lrama 0.6.1 → 0.6.3

data/lib/lrama/grammar/symbol.rb

@@ -11,7 +11,7 @@ module Lrama
       attr_reader :term
       attr_writer :eof_symbol, :error_symbol, :undef_symbol, :accept_symbol
 
-      def initialize(id:, alias_name: nil, number: nil, tag: nil, term:, token_id: nil, nullable: nil, precedence: nil, printer: nil)
+      def initialize(id:, term:, alias_name: nil, number: nil, tag: nil, token_id: nil, nullable: nil, precedence: nil, printer: nil)
         @id = id
         @alias_name = alias_name
         @number = number

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

@@ -0,0 +1,276 @@
+module Lrama
+  class Grammar
+    class Symbols
+      class Resolver
+        attr_reader :terms, :nterms
+
+        def initialize
+          @terms = []
+          @nterms = []
+        end
+
+        def symbols
+          @symbols ||= (@terms + @nterms)
+        end
+
+        def sort_by_number!
+          symbols.sort_by!(&:number)
+        end
+
+        def add_term(id:, alias_name: nil, tag: nil, token_id: nil, replace: false)
+          if token_id && (sym = find_symbol_by_token_id(token_id))
+            if replace
+              sym.id = id
+              sym.alias_name = alias_name
+              sym.tag = tag
+            end
+
+            return sym
+          end
+
+          if (sym = find_symbol_by_id(id))
+            return sym
+          end
+
+          @symbols = nil
+          term = Symbol.new(
+            id: id, alias_name: alias_name, number: nil, tag: tag,
+            term: true, token_id: token_id, nullable: false
+          )
+          @terms << term
+          term
+        end
+
+        def add_nterm(id:, alias_name: nil, tag: nil)
+          return if find_symbol_by_id(id)
+
+          @symbols = nil
+          nterm = Symbol.new(
+            id: id, alias_name: alias_name, number: nil, tag: tag,
+            term: false, token_id: nil, nullable: nil,
+          )
+          @nterms << nterm
+          nterm
+        end
+
+        def find_symbol_by_s_value(s_value)
+          symbols.find { |s| s.id.s_value == s_value }
+        end
+
+        def find_symbol_by_s_value!(s_value)
+          find_symbol_by_s_value(s_value) || (raise "Symbol not found: #{s_value}")
+        end
+
+        def find_symbol_by_id(id)
+          symbols.find do |s|
+            s.id == id || s.alias_name == id.s_value
+          end
+        end
+
+        def find_symbol_by_id!(id)
+          find_symbol_by_id(id) || (raise "Symbol not found: #{id}")
+        end
+
+        def find_symbol_by_token_id(token_id)
+          symbols.find {|s| s.token_id == token_id }
+        end
+
+        def find_symbol_by_number!(number)
+          sym = symbols[number]
+
+          raise "Symbol not found: #{number}" unless sym
+          raise "[BUG] Symbol number mismatch. #{number}, #{sym}" if sym.number != number
+
+          sym
+        end
+
+        def fill_symbol_number
+          # YYEMPTY = -2
+          # YYEOF   =  0
+          # YYerror =  1
+          # YYUNDEF =  2
+          @number = 3
+          fill_terms_number
+          fill_nterms_number
+        end
+
+        def fill_nterm_type(types)
+          types.each do |type|
+            nterm = find_nterm_by_id!(type.id)
+            nterm.tag = type.tag
+          end
+        end
+
+        def fill_printer(printers)
+          symbols.each do |sym|
+            printers.each do |printer|
+              printer.ident_or_tags.each do |ident_or_tag|
+                case ident_or_tag
+                when Lrama::Lexer::Token::Ident
+                  sym.printer = printer if sym.id == ident_or_tag
+                when Lrama::Lexer::Token::Tag
+                  sym.printer = printer if sym.tag == ident_or_tag
+                else
+                  raise "Unknown token type. #{printer}"
+                end
+              end
+            end
+          end
+        end
+
+        def fill_error_token(error_tokens)
+          symbols.each do |sym|
+            error_tokens.each do |token|
+              token.ident_or_tags.each do |ident_or_tag|
+                case ident_or_tag
+                when Lrama::Lexer::Token::Ident
+                  sym.error_token = token if sym.id == ident_or_tag
+                when Lrama::Lexer::Token::Tag
+                  sym.error_token = token if sym.tag == ident_or_tag
+                else
+                  raise "Unknown token type. #{token}"
+                end
+              end
+            end
+          end
+        end
+
+        def token_to_symbol(token)
+          case token
+          when Lrama::Lexer::Token
+            find_symbol_by_id!(token)
+          else
+            raise "Unknown class: #{token}"
+          end
+        end
+
+        def validate!
+          validate_number_uniqueness!
+          validate_alias_name_uniqueness!
+        end
+
+        private
+
+        def find_nterm_by_id!(id)
+          @nterms.find do |s|
+            s.id == id
+          end || (raise "Symbol not found: #{id}")
+        end
+
+        def fill_terms_number
+          # Character literal in grammar file has
+          # token id corresponding to ASCII code by default,
+          # so start token_id from 256.
+          token_id = 256
+
+          @terms.each do |sym|
+            while used_numbers[@number] do
+              @number += 1
+            end
+
+            if sym.number.nil?
+              sym.number = @number
+              used_numbers[@number] = true
+              @number += 1
+            end
+
+            # If id is Token::Char, it uses ASCII code
+            if sym.token_id.nil?
+              if sym.id.is_a?(Lrama::Lexer::Token::Char)
+                # Ignore ' on the both sides
+                case sym.id.s_value[1..-2]
+                when "\\b"
+                  sym.token_id = 8
+                when "\\f"
+                  sym.token_id = 12
+                when "\\n"
+                  sym.token_id = 10
+                when "\\r"
+                  sym.token_id = 13
+                when "\\t"
+                  sym.token_id = 9
+                when "\\v"
+                  sym.token_id = 11
+                when "\""
+                  sym.token_id = 34
+                when "'"
+                  sym.token_id = 39
+                when "\\\\"
+                  sym.token_id = 92
+                when /\A\\(\d+)\z/
+                  unless (id = Integer($1, 8)).nil?
+                    sym.token_id = id
+                  else
+                    raise "Unknown Char s_value #{sym}"
+                  end
+                when /\A(.)\z/
+                  unless (id = $1&.bytes&.first).nil?
+                    sym.token_id = id
+                  else
+                    raise "Unknown Char s_value #{sym}"
+                  end
+                else
+                  raise "Unknown Char s_value #{sym}"
+                end
+              else
+                sym.token_id = token_id
+                token_id += 1
+              end
+            end
+          end
+        end
+
+        def fill_nterms_number
+          token_id = 0
+
+          @nterms.each do |sym|
+            while used_numbers[@number] do
+              @number += 1
+            end
+
+            if sym.number.nil?
+              sym.number = @number
+              used_numbers[@number] = true
+              @number += 1
+            end
+
+            if sym.token_id.nil?
+              sym.token_id = token_id
+              token_id += 1
+            end
+          end
+        end
+
+        def used_numbers
+          return @used_numbers if defined?(@used_numbers)
+
+          @used_numbers = {}
+          symbols.map(&:number).each do |n|
+            @used_numbers[n] = true
+          end
+          @used_numbers
+        end
+
+        def validate_number_uniqueness!
+          invalid = symbols.group_by(&:number).select do |number, syms|
+            syms.count > 1
+          end
+
+          return if invalid.empty?
+
+          raise "Symbol number is duplicated. #{invalid}"
+        end
+
+        def validate_alias_name_uniqueness!
+          invalid = symbols.select(&:alias_name).group_by(&:alias_name).select do |alias_name, syms|
+            syms.count > 1
+          end
+
+          return if invalid.empty?
+
+          raise "Symbol alias name is duplicated. #{invalid}"
+        end
+      end
+    end
+  end
+end

data/lib/lrama/grammar/symbols.rb

@@ -0,0 +1 @@
+require_relative "symbols/resolver"

data/lib/lrama/grammar.rb

@@ -1,16 +1,18 @@
+require "forwardable"
 require "lrama/grammar/auxiliary"
 require "lrama/grammar/binding"
 require "lrama/grammar/code"
 require "lrama/grammar/counter"
 require "lrama/grammar/error_token"
+require "lrama/grammar/parameterizing_rule"
 require "lrama/grammar/percent_code"
 require "lrama/grammar/precedence"
 require "lrama/grammar/printer"
 require "lrama/grammar/reference"
 require "lrama/grammar/rule"
 require "lrama/grammar/rule_builder"
-require "lrama/grammar/parameterizing_rule"
 require "lrama/grammar/symbol"
+require "lrama/grammar/symbols"
 require "lrama/grammar/type"
 require "lrama/grammar/union"
 require "lrama/lexer"
@@ -18,13 +20,22 @@ require "lrama/lexer"
 module Lrama
   # Grammar is the result of parsing an input grammar file
   class Grammar
+    extend Forwardable
+
     attr_reader :percent_codes, :eof_symbol, :error_symbol, :undef_symbol, :accept_symbol, :aux
     attr_accessor :union, :expect,
                   :printers, :error_tokens,
                   :lex_param, :parse_param, :initial_action,
-                  :symbols, :types,
+                  :after_shift, :before_reduce, :after_reduce, :after_shift_error_token, :after_pop_stack,
+                  :symbols_resolver, :types,
                   :rules, :rule_builders,
-                  :sym_to_rules
+                  :sym_to_rules, :no_stdlib
+
+    def_delegators "@symbols_resolver", :symbols, :nterms, :terms, :add_nterm, :add_term,
+                                        :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_error_token, :sort_by_number!
+
 
     def initialize(rule_counter)
       @rule_counter = rule_counter
@@ -33,7 +44,7 @@ module Lrama
       @percent_codes = []
       @printers = []
       @error_tokens = []
-      @symbols = []
+      @symbols_resolver = Grammar::Symbols::Resolver.new
       @types = []
       @rule_builders = []
       @rules = []
@@ -45,6 +56,7 @@ module Lrama
       @undef_symbol = nil
       @accept_symbol = nil
       @aux = Auxiliary.new
+      @no_stdlib = false
 
       append_special_symbols
     end
@@ -61,44 +73,6 @@ module Lrama
       @error_tokens << ErrorToken.new(ident_or_tags: ident_or_tags, token_code: token_code, lineno: lineno)
     end
 
-    def add_term(id:, alias_name: nil, tag: nil, token_id: nil, replace: false)
-      if token_id && (sym = @symbols.find {|s| s.token_id == token_id })
-        if replace
-          sym.id = id
-          sym.alias_name = alias_name
-          sym.tag = tag
-        end
-
-        return sym
-      end
-
-      if (sym = @symbols.find {|s| s.id == id })
-        return sym
-      end
-
-      sym = Symbol.new(
-        id: id, alias_name: alias_name, number: nil, tag: tag,
-        term: true, token_id: token_id, nullable: false
-      )
-      @symbols << sym
-      @terms = nil
-
-      return sym
-    end
-
-    def add_nterm(id:, alias_name: nil, tag: nil)
-      return if @symbols.find {|s| s.id == id }
-
-      sym = Symbol.new(
-        id: id, alias_name: alias_name, number: nil, tag: tag,
-        term: false, token_id: nil, nullable: nil,
-      )
-      @symbols << sym
-      @nterms = nil
-
-      return sym
-    end
-
     def add_type(id:, tag:)
       @types << Type.new(id: id, tag: tag)
     end
@@ -136,6 +110,14 @@ module Lrama
       @parameterizing_rule_resolver.add_parameterizing_rule(rule)
     end
 
+    def parameterizing_rules
+      @parameterizing_rule_resolver.rules
+    end
+
+    def insert_before_parameterizing_rules(rules)
+      @parameterizing_rule_resolver.rules = rules + @parameterizing_rule_resolver.rules
+    end
+
     def prologue_first_lineno=(prologue_first_lineno)
       @aux.prologue_first_lineno = prologue_first_lineno
     end
@@ -156,13 +138,9 @@ module Lrama
       normalize_rules
       collect_symbols
       set_lhs_and_rhs
-      fill_symbol_number
       fill_default_precedence
+      fill_symbols
       fill_sym_to_rules
-      fill_nterm_type
-      fill_symbol_printer
-      fill_symbol_error_token
-      @symbols.sort_by!(&:number)
       compute_nullable
       compute_first_set
     end
@@ -171,40 +149,10 @@ module Lrama
     #
     # * Validation for no_declared_type_reference
     def validate!
-      validate_symbol_number_uniqueness!
-      validate_symbol_alias_name_uniqueness!
+      @symbols_resolver.validate!
       validate_rule_lhs_is_nterm!
     end
 
-    def find_symbol_by_s_value(s_value)
-      @symbols.find do |sym|
-        sym.id.s_value == s_value
-      end
-    end
-
-    def find_symbol_by_s_value!(s_value)
-      find_symbol_by_s_value(s_value) || (raise "Symbol not found: #{s_value}")
-    end
-
-    def find_symbol_by_id(id)
-      @symbols.find do |sym|
-        sym.id == id || sym.alias_name == id.s_value
-      end
-    end
-
-    def find_symbol_by_id!(id)
-      find_symbol_by_id(id) || (raise "Symbol not found: #{id}")
-    end
-
-    def find_symbol_by_number!(number)
-      sym = @symbols[number]
-
-      raise "Symbol not found: #{number}" unless sym
-      raise "[BUG] Symbol number mismatch. #{number}, #{sym}" if sym.number != number
-
-      sym
-    end
-
     def find_rules_by_symbol!(sym)
       find_rules_by_symbol(sym) || (raise "Rules for #{sym} not found")
     end
@@ -213,28 +161,12 @@ module Lrama
       @sym_to_rules[sym.number]
     end
 
-    def terms_count
-      terms.count
-    end
-
-    def terms
-      @terms ||= @symbols.select(&:term?)
-    end
-
-    def nterms_count
-      nterms.count
-    end
-
-    def nterms
-      @nterms ||= @symbols.select(&:nterm?)
-    end
-
     private
 
     def compute_nullable
       @rules.each do |rule|
         case
-        when rule.rhs.empty?
+        when rule.empty_rule?
           rule.nullable = true
         when rule.rhs.any?(&:term)
           rule.nullable = false
@@ -275,7 +207,7 @@ module Lrama
         rule.nullable = false
       end
 
-      nterms.select {|r| r.nullable.nil? }.each do |nterm|
+      nterms.select {|e| e.nullable.nil? }.each do |nterm|
         nterm.nullable = false
       end
     end
@@ -321,12 +253,6 @@ module Lrama
       end
     end
 
-    def find_nterm_by_id!(id)
-      nterms.find do |nterm|
-        nterm.id == id
-      end || (raise "Nterm not found: #{id}")
-    end
-
     def append_special_symbols
       # YYEMPTY (token_id: -2, number: -2) is added when a template is evaluated
       # term = add_term(id: Token.new(Token::Ident, "YYEMPTY"), token_id: -2)
@@ -388,79 +314,6 @@ module Lrama
       end
     end
 
-    # Fill #number and #token_id
-    def fill_symbol_number
-      # Character literal in grammar file has
-      # token id corresponding to ASCII code by default,
-      # so start token_id from 256.
-      token_id = 256
-
-      # YYEMPTY = -2
-      # YYEOF   =  0
-      # YYerror =  1
-      # YYUNDEF =  2
-      number = 3
-
-      nterm_token_id = 0
-      used_numbers = {}
-
-      @symbols.map(&:number).each do |n|
-        used_numbers[n] = true
-      end
-
-      (@symbols.select(&:term?) + @symbols.select(&:nterm?)).each do |sym|
-        while used_numbers[number] do
-          number += 1
-        end
-
-        if sym.number.nil?
-          sym.number = number
-          number += 1
-        end
-
-        # If id is Token::Char, it uses ASCII code
-        if sym.term? && sym.token_id.nil?
-          if sym.id.is_a?(Lrama::Lexer::Token::Char)
-            # Ignore ' on the both sides
-            case sym.id.s_value[1..-2]
-            when "\\b"
-              sym.token_id = 8
-            when "\\f"
-              sym.token_id = 12
-            when "\\n"
-              sym.token_id = 10
-            when "\\r"
-              sym.token_id = 13
-            when "\\t"
-              sym.token_id = 9
-            when "\\v"
-              sym.token_id = 11
-            when "\""
-              sym.token_id = 34
-            when "'"
-              sym.token_id = 39
-            when "\\\\"
-              sym.token_id = 92
-            when /\A\\(\d+)\z/
-              sym.token_id = Integer($1, 8)
-            when /\A(.)\z/
-              sym.token_id = $1.bytes.first
-            else
-              raise "Unknown Char s_value #{sym}"
-            end
-          else
-            sym.token_id = token_id
-            token_id += 1
-          end
-        end
-
-        if sym.nterm? && sym.token_id.nil?
-          sym.token_id = nterm_token_id
-          nterm_token_id += 1
-        end
-      end
-    end
-
     def set_lhs_and_rhs
       @rules.each do |rule|
         rule.lhs = token_to_symbol(rule._lhs) if rule._lhs
@@ -471,15 +324,6 @@ module Lrama
       end
     end
 
-    def token_to_symbol(token)
-      case token
-      when Lrama::Lexer::Token
-        find_symbol_by_id!(token)
-      else
-        raise "Unknown class: #{token}"
-      end
-    end
-
     # Rule inherits precedence from the last term in RHS.
     #
     # https://www.gnu.org/software/bison/manual/html_node/How-Precedence.html
@@ -497,6 +341,14 @@ module Lrama
       end
     end
 
+    def fill_symbols
+      fill_symbol_number
+      fill_nterm_type(@types)
+      fill_printer(@printers)
+      fill_error_token(@error_tokens)
+      sort_by_number!
+    end
+
     def fill_sym_to_rules
       @rules.each do |rule|
         key = rule.lhs.number
@@ -505,68 +357,6 @@ module Lrama
       end
     end
 
-    # Fill nterm's tag defined by %type decl
-    def fill_nterm_type
-      @types.each do |type|
-        nterm = find_nterm_by_id!(type.id)
-        nterm.tag = type.tag
-      end
-    end
-
-    def fill_symbol_printer
-      @symbols.each do |sym|
-        @printers.each do |printer|
-          printer.ident_or_tags.each do |ident_or_tag|
-            case ident_or_tag
-            when Lrama::Lexer::Token::Ident
-              sym.printer = printer if sym.id == ident_or_tag
-            when Lrama::Lexer::Token::Tag
-              sym.printer = printer if sym.tag == ident_or_tag
-            else
-              raise "Unknown token type. #{printer}"
-            end
-          end
-        end
-      end
-    end
-
-    def fill_symbol_error_token
-      @symbols.each do |sym|
-        @error_tokens.each do |error_token|
-          error_token.ident_or_tags.each do |ident_or_tag|
-            case ident_or_tag
-            when Lrama::Lexer::Token::Ident
-              sym.error_token = error_token if sym.id == ident_or_tag
-            when Lrama::Lexer::Token::Tag
-              sym.error_token = error_token if sym.tag == ident_or_tag
-            else
-              raise "Unknown token type. #{error_token}"
-            end
-          end
-        end
-      end
-    end
-
-    def validate_symbol_number_uniqueness!
-      invalid = @symbols.group_by(&:number).select do |number, syms|
-        syms.count > 1
-      end
-
-      return if invalid.empty?
-
-      raise "Symbol number is duplicated. #{invalid}"
-    end
-
-    def validate_symbol_alias_name_uniqueness!
-      invalid = @symbols.select(&:alias_name).group_by(&:alias_name).select do |alias_name, syms|
-        syms.count > 1
-      end
-
-      return if invalid.empty?
-
-      raise "Symbol alias name is duplicated. #{invalid}"
-    end
-
     def validate_rule_lhs_is_nterm!
       errors = []