lrama 0.5.10 → 0.5.12

data/lib/lrama/version.rb

@@ -1,3 +1,3 @@
 module Lrama
-  VERSION = "0.5.10".freeze
+  VERSION = "0.5.12".freeze
 end

data/lib/lrama.rb

@@ -13,6 +13,5 @@ require "lrama/report"
 require "lrama/state"
 require "lrama/states"
 require "lrama/states_reporter"
-require "lrama/type"
 require "lrama/version"
 require "lrama/warning"

data/parser.y

@@ -1,5 +1,5 @@
 class Lrama::Parser
-  expect 1
+  expect 0
 
   token C_DECLARATION CHARACTER IDENT_COLON IDENTIFIER INTEGER STRING TAG
 
@@ -31,7 +31,6 @@ rule
   bison_declaration: grammar_declaration
                    | "%expect" INTEGER { @grammar.expect = val[1] }
                    | "%define" variable value
-                   | "%require" STRING
                    | "%param" params
                    | "%lex-param" params
                        {
@@ -327,27 +326,24 @@ rule
            builder.add_rhs(token)
            result = builder
          }
-     | rhs IDENTIFIER parameterizing_suffix
+     | rhs IDENTIFIER parameterizing_suffix tag_opt
          {
            token = Lrama::Lexer::Token::Parameterizing.new(s_value: val[2], location: @lexer.location, args: [val[1]])
            builder = val[0]
            builder.add_rhs(token)
+           builder.lhs_tag = val[3]
+           builder.line = val[1].first_line
            result = builder
          }
-     | rhs IDENTIFIER "(" symbol ")"
+     | rhs IDENTIFIER "(" parameterizing_args ")" tag_opt
          {
-           token = Lrama::Lexer::Token::Parameterizing.new(s_value: val[1].s_value, location: @lexer.location, args: [val[3]])
+           token = Lrama::Lexer::Token::Parameterizing.new(s_value: val[1].s_value, location: @lexer.location, args: val[3])
            builder = val[0]
            builder.add_rhs(token)
+           builder.lhs_tag = val[5]
+           builder.line = val[1].first_line
            result = builder
          }
-     | rhs IDENTIFIER "(" symbol "," symbol ")"
-        {
-          token = Lrama::Lexer::Token::Parameterizing.new(s_value: val[1].s_value, location: @lexer.location, args: [val[3], val[5]])
-          builder = val[0]
-          builder.add_rhs(token)
-          result = builder
-        }
      | rhs "{"
          {
            if @prec_seen
@@ -362,10 +358,10 @@ rule
          }
        "}" named_ref_opt
          {
-           token = val[3]
-           token.alias_name = val[6]
+           user_code = val[3]
+           user_code.alias_name = val[6]
            builder = val[0]
-           builder.user_code = token
+           builder.user_code = user_code
            result = builder
          }
      | rhs "%prec" symbol
@@ -381,6 +377,9 @@ rule
                        | "+"
                        | "*"
 
+  parameterizing_args: symbol { result = [val[0]] }
+                     | parameterizing_args ',' symbol { result = val[0].append(val[2]) }
+
   named_ref_opt: # empty
                | '[' IDENTIFIER ']' { result = val[1].s_value }
 
@@ -412,6 +411,9 @@ rule
                       | TAG
 
   string_as_id: STRING { result = Lrama::Lexer::Token::Ident.new(s_value: val[0]) }
+
+  tag_opt: # empty
+         | TAG
 end
 
 ---- inner

data/rbs_collection.lock.yaml

@@ -1,10 +1,4 @@
 ---
-sources:
-- type: git
-  name: ruby/gem_rbs_collection
-  revision: 25286c51a19927f28623aee3cd36655f902399ba
-  remote: https://github.com/ruby/gem_rbs_collection.git
-  repo_dir: gems
 path: ".gem_rbs_collection"
 gems:
 - name: erb
@@ -24,7 +18,7 @@ gems:
   source:
     type: git
     name: ruby/gem_rbs_collection
-    revision: 2de2d4535caba275f3b8533684aab110d921f553
+    revision: 4b0d2f72e63b6c3e92dc54e19ce23dd24524f9a7
     remote: https://github.com/ruby/gem_rbs_collection.git
     repo_dir: gems
 - name: stackprof
@@ -32,7 +26,7 @@ gems:
   source:
     type: git
     name: ruby/gem_rbs_collection
-    revision: 28208148c7e64a25e9b86b9723b4c3a2cef14e81
+    revision: 4b0d2f72e63b6c3e92dc54e19ce23dd24524f9a7
     remote: https://github.com/ruby/gem_rbs_collection.git
     repo_dir: gems
 - name: strscan

data/sig/lrama/grammar/error_token.rbs

@@ -0,0 +1,11 @@
+module Lrama
+  class Grammar
+    class ErrorToken
+      attr_accessor ident_or_tags: Array[Lexer::Token::Ident | Lexer::Token::Tag]
+      attr_accessor token_code: Symbol
+      attr_accessor lineno: Integer
+
+      def translated_code: (Lexer::Token? tag) -> String
+    end
+  end
+end

data/sig/lrama/grammar/parameterizing_rules/builder/base.rbs

@@ -0,0 +1,28 @@
+module Lrama
+  class Grammar
+    class ParameterizingRules
+      class Builder
+        class Base
+          attr_reader build_token: Lexer::Token::Ident
+
+          def initialize: (Lexer::Token::Parameterizing token, Counter rule_counter, untyped lhs_tag, Lexer::Token::UserCode? user_code, Lexer::Token? precedence_sym, Integer? line) -> void
+          def build: () -> Array[Rule]
+
+          @args: Array[Lexer::Token]
+          @token: Lexer::Token::Parameterizing
+          @key: Symbol
+          @rule_counter: Counter
+          @lhs_tag: untyped
+          @user_code: Lexer::Token::UserCode?
+          @precedence_sym: Lexer::Token?
+          @line: Integer?
+          @expected_argument_num: Integer
+
+          private
+
+          def validate_argument_number!: () -> void
+        end
+      end
+    end
+  end
+end

data/sig/lrama/grammar/parameterizing_rules/builder/list.rbs

@@ -0,0 +1,10 @@
+module Lrama
+  class Grammar
+    class ParameterizingRules
+      class Builder
+        class List < Base
+        end
+      end
+    end
+  end
+end

data/sig/lrama/grammar/parameterizing_rules/builder/nonempty_list.rbs

@@ -0,0 +1,10 @@
+module Lrama
+  class Grammar
+    class ParameterizingRules
+      class Builder
+        class NonemptyList < Base
+        end
+      end
+    end
+  end
+end

data/sig/lrama/grammar/parameterizing_rules/builder/option.rbs

@@ -0,0 +1,10 @@
+module Lrama
+  class Grammar
+    class ParameterizingRules
+      class Builder
+        class Option < Base
+        end
+      end
+    end
+  end
+end

data/sig/lrama/grammar/parameterizing_rules/builder/separated_list.rbs

@@ -0,0 +1,13 @@
+module Lrama
+  class Grammar
+    class ParameterizingRules
+      class Builder
+        class SeparatedList < Base
+          @separator: Lexer::Token
+
+          def initialize: (Lexer::Token token, Counter rule_counter, untyped lhs_tag, Lexer::Token::UserCode? user_code, Lexer::Token? precedence_sym, Integer? line) -> void
+        end
+      end
+    end
+  end
+end

data/sig/lrama/grammar/parameterizing_rules/builder/separated_nonempty_list.rbs

@@ -0,0 +1,13 @@
+module Lrama
+  class Grammar
+    class ParameterizingRules
+      class Builder
+        class SeparatedNonemptyList < Base
+          @separator: Lexer::Token
+
+          def initialize: (Lexer::Token token, Counter rule_counter, untyped lhs_tag, Lexer::Token::UserCode? user_code, Lexer::Token? precedence_sym, Integer? line) -> void
+        end
+      end
+    end
+  end
+end

data/sig/lrama/grammar/parameterizing_rules/builder.rbs

@@ -2,8 +2,22 @@ module Lrama
   class Grammar
     class ParameterizingRules
       class Builder
-        def initialize: (Lexer::Token token, Counter rule_counter, Lexer::Token lhs, Lexer::Token::UserCode? user_code, Lexer::Token? precedence_sym, Integer? line) -> void
+        RULES: Hash[Symbol, singleton(Base)]
+
+        @token: Lexer::Token::Parameterizing
+        @key: Symbol
+        @rule_counter: Counter
+        @lhs_tag: untyped
+        @user_code: Lexer::Token::UserCode?
+        @precedence_sym: Lexer::Token?
+        @line: Integer?
+        @builder: Grammar::ParameterizingRules::Builder::Base
+
+        def initialize: (Lexer::Token token, Counter rule_counter, untyped lhs_tag, Lexer::Token::UserCode? user_code, Lexer::Token? precedence_sym, Integer? line) -> void
         def build: () -> Array[Rule]
+        def build_token: () -> Lexer::Token
+        def create_builder: () -> void
+        def validate_key!: () -> void
       end
     end
   end

data/sig/lrama/grammar/reference.rbs

@@ -1,7 +1,7 @@
 module Lrama
   class Grammar
     class Reference
-      attr_accessor type: Symbol
+      attr_accessor type: ::Symbol
       attr_accessor name: String
       attr_accessor index: Integer
       attr_accessor ex_tag: Lexer::Token?
@@ -10,7 +10,7 @@ module Lrama
       attr_accessor position_in_rhs: Integer?
 
       def initialize: (
-        type: Symbol, ?name: String, ?index: Integer, ?ex_tag: Lexer::Token?,
+        type: ::Symbol, ?name: String, ?index: Integer, ?ex_tag: Lexer::Token?,
         first_column: Integer, last_column: Integer,
         ?position_in_rhs: Integer?
       ) -> void

data/sig/lrama/grammar/rule.rbs

@@ -4,7 +4,7 @@ module Lrama
       attr_accessor original_rule: Rule
 
       def initialize: (
-        ?id: untyped, ?_lhs: untyped, ?lhs: untyped, ?_rhs: untyped, ?rhs: untyped,
+        ?id: untyped, ?_lhs: untyped, ?lhs: untyped, ?lhs_tag: untyped, ?_rhs: untyped, ?rhs: untyped,
         ?token_code: untyped, ?position_in_original_rule_rhs: untyped, ?nullable: untyped,
         ?precedence_sym: untyped, ?lineno: untyped
       ) -> void

data/sig/lrama/grammar/rule_builder.rbs

@@ -2,6 +2,7 @@ module Lrama
   class Grammar
     class RuleBuilder
       attr_accessor lhs: Lexer::Token
+      attr_accessor lhs_tag: untyped
       attr_accessor line: Integer?
       attr_reader rhs: Array[Lexer::Token]
       attr_reader user_code: Lexer::Token::UserCode?

data/sig/lrama/grammar/symbol.rbs

@@ -0,0 +1,37 @@
+module Lrama
+  class Grammar
+    class Symbol
+      attr_accessor id: Lexer::Token
+      attr_accessor alias_name: String
+      attr_accessor number: Integer
+      attr_accessor tag: Lexer::Token?
+      attr_accessor term: bool
+      attr_accessor token_id: Integer
+      attr_accessor nullable: bool
+      attr_accessor precedence: Precedence?
+      attr_accessor printer: Printer?
+      attr_accessor error_token: ErrorToken
+
+      attr_accessor first_set: Set[Array[Symbol]]
+      attr_accessor first_set_bitmap: Integer
+      attr_writer eof_symbol: Symbol
+      attr_writer error_symbol: Symbol
+      attr_writer undef_symbol: Symbol
+      attr_writer accept_symbol: Symbol
+
+      def initialize: (
+          id: Lexer::Token, alias_name: String?, number: Integer?, tag: Lexer::Token?,
+          term: bool, token_id: Integer?, nullable: bool?, precedence: Precedence?, printer: Printer?) -> void
+
+      def term?: () -> bool
+      def nterm?: () -> bool
+      def eof_symbol?: () -> bool
+      def error_symbol?: () -> bool
+      def undef_symbol?: () -> bool
+      def accept_symbol?: () -> bool
+      def display_name: () -> String
+      def enum_name: () -> String
+      def comment: () -> String
+    end
+  end
+end

data/sig/lrama/lexer/token/parameterizing.rbs

@@ -2,7 +2,9 @@ module Lrama
   class Lexer
     class Token
       class Parameterizing < Token
-        attr_accessor args: Array[Lrama::Lexer::Token]
+        attr_accessor args: Array[Lexer::Token]
+
+        def initialize: (s_value: String, ?alias_name: String, ?location: Location, ?args: Array[Lexer::Token]) -> void
 
         def option?: () -> bool
         def nonempty_list?: () -> bool

data/sig/lrama/lexer/token.rbs

@@ -1,12 +1,12 @@
 module Lrama
   class Lexer
     class Token
-      attr_accessor s_value: String
+      attr_reader s_value: String
       attr_accessor alias_name: String
-      attr_accessor location: Location
+      attr_reader location: Location
       attr_accessor referred: bool
 
-      def initialize: (?s_value: String, ?alias_name: String, ?location: Location) -> void
+      def initialize: (s_value: String, ?alias_name: String, ?location: Location) -> void
 
       def to_s: () -> String
       def referred_by?: (String string) -> bool

data/template/bison/yacc.c

@@ -72,7 +72,6 @@
 <%- if output.aux.prologue -%>
 /* First part of user prologue.  */
 #line <%= output.aux.prologue_first_lineno %> "<%= output.grammar_file_path %>"
-
 <%= output.aux.prologue %>
 #line [@oline@] [@ofile@]
 <%- end -%>
@@ -2048,7 +2047,6 @@ yyreturnlab:
 <%# b4_percent_code_get([[epilogue]]) -%>
 <%- if output.aux.epilogue -%>
 #line <%= output.aux.epilogue_first_lineno - 1 %> "<%= output.grammar_file_path %>"
-
 <%= output.aux.epilogue -%>
 <%- end -%>
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: lrama
 version: !ruby/object:Gem::Version
-  version: 0.5.10
+  version: 0.5.12
 platform: ruby
 authors:
 - Yuichiro Kaneko
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2023-11-18 00:00:00.000000000 Z
+date: 2023-12-07 00:00:00.000000000 Z
 dependencies: []
 description: LALR (1) parser generator written by Ruby
 email:
@@ -27,10 +27,10 @@ files:
 - Gemfile
 - LEGAL.md
 - MIT
+- NEWS.md
 - README.md
 - Rakefile
 - Steepfile
-- doc/TODO.md
 - exe/lrama
 - lib/lrama.rb
 - lib/lrama/bitmap.rb
@@ -69,6 +69,7 @@ files:
 - lib/lrama/grammar/rule.rb
 - lib/lrama/grammar/rule_builder.rb
 - lib/lrama/grammar/symbol.rb
+- lib/lrama/grammar/type.rb
 - lib/lrama/grammar/union.rb
 - lib/lrama/lexer.rb
 - lib/lrama/lexer/location.rb
@@ -94,7 +95,6 @@ files:
 - lib/lrama/states.rb
 - lib/lrama/states/item.rb
 - lib/lrama/states_reporter.rb
-- lib/lrama/type.rb
 - lib/lrama/version.rb
 - lib/lrama/warning.rb
 - lrama.gemspec
@@ -110,13 +110,21 @@ files:
 - sig/lrama/grammar/code.rbs
 - sig/lrama/grammar/code/printer_code.rbs
 - sig/lrama/grammar/counter.rbs
+- sig/lrama/grammar/error_token.rbs
 - sig/lrama/grammar/parameterizing_rules/builder.rbs
+- sig/lrama/grammar/parameterizing_rules/builder/base.rbs
+- sig/lrama/grammar/parameterizing_rules/builder/list.rbs
+- sig/lrama/grammar/parameterizing_rules/builder/nonempty_list.rbs
+- sig/lrama/grammar/parameterizing_rules/builder/option.rbs
+- sig/lrama/grammar/parameterizing_rules/builder/separated_list.rbs
+- sig/lrama/grammar/parameterizing_rules/builder/separated_nonempty_list.rbs
 - sig/lrama/grammar/percent_code.rbs
 - sig/lrama/grammar/precedence.rbs
 - sig/lrama/grammar/printer.rbs
 - sig/lrama/grammar/reference.rbs
 - sig/lrama/grammar/rule.rbs
 - sig/lrama/grammar/rule_builder.rbs
+- sig/lrama/grammar/symbol.rbs
 - sig/lrama/lexer/location.rbs
 - sig/lrama/lexer/token.rbs
 - sig/lrama/lexer/token/char.rbs

data/doc/TODO.md

@@ -1,59 +0,0 @@
-# TODO
-
-* command
-* lexer
-  * [x] Basic functionalities
-* parser
-  * [x] Basic functionalities
-  * [x] Precedence in grammar
-* LALR
-  * [x] compute_nullable
-  * [x] compute_lr0_states
-  * [x] Direct Read Sets
-  * [x] Reads Relation
-  * [x] Read Sets
-  * [x] Includes Relation
-  * [x] Lookback Relation
-  * [x] Follow Sets
-  * [x] Look-Ahead Sets
-  * [x] Precedence support
-  * [x] Conflict check
-  * [x] Algorithm Digraph
-  * [ ] Conflict resolution
-    * [x] Do not generate default action if states have conflicts
-    * [ ] Fix number of s/r conflicts of basic.y. See basic.output file generated by Bison.
-* Rendering
-  * [x] Table compaction
-  * [x] -d option
-  * yacc.c
-    * [x] %lex-param
-    * [x] %parse-param
-    * [x] %printer
-    * [x] Replace $, @ in user codes
-    * [x] `[@oline@]`
-    * [ ] b4_symbol (for eof, error and so on)
-    * Assumption
-      * b4_locations_if is true
-      * b4_pure_if is true
-      * b4_pull_if is false
-      * b4_lac_if is false
-* Performance improvement
-  * [ ]
-* Licenses
-  * [x] Write down something about licenses
-* Reporting
-  * [ ] Bison style
-    * [ ] Wrap not selected reduce with "[]". See basic.output file generated by Bison.
-* Counterexamples
-  * [x] Nonunifying Counterexamples
-  * [ ] Unifying Counterexamples
-  * [ ] Performance improvement using reverse_transitions and reverse_productions
-* Error Tolerance
-  * [x] Corchuelo et al. algorithm with N = 1 (this means the next token when error is raised)
-  * [x] Add new decl for error token semantic value initialization (%error-token)
-  * [x] Use YYMALLOC & YYFREE
-* Lex state
-* CI
-  * [x] Setup CI
-  * [x] Add ruby 3.1 or under
-  * [x] Add integration tests which installs Lrama, build ruby and run `make test`

data/lib/lrama/type.rb

@@ -1,4 +0,0 @@
-module Lrama
-  class Type < Struct.new(:id, :tag, keyword_init: true)
-  end
-end