Lrama v0.6.4

tool/lrama/NEWS.md

@@ -1,5 +1,69 @@
 # NEWS for Lrama
 
+## Lrama 0.6.4 (2024-03-22)
+
+### Parameterizing rules (preceded, terminated, delimited)
+
+Support `preceded`, `terminated` and `delimited` rules.
+
+```
+program: preceded(opening, X)
+
+// Expanded to
+
+program: preceded_opening_X
+preceded_opening_X: opening X
+```
+
+```
+program: terminated(X, closing)
+
+// Expanded to
+
+program: terminated_X_closing
+terminated_X_closing: X closing
+```
+
+```
+program: delimited(opening, X, closing)
+
+// Expanded to
+
+program: delimited_opening_X_closing
+delimited_opening_X_closing: opening X closing
+```
+
+https://github.com/ruby/lrama/pull/382
+
+### Support `%destructor` declaration
+
+User can set codes for freeing semantic value resources by using `%destructor`.
+In general, these resources are freed by actions or after parsing.
+However if syntax error happens in parsing, these codes may not be executed.
+Codes associated to `%destructor` are executed when semantic value is popped from the stack by an error.
+
+```
+%token <val1> NUM
+%type <val2> expr2
+%type <val3> expr
+
+%destructor {
+    printf("destructor for val1: %d\n", $$);
+} <val1> // printer for TAG
+
+%destructor {
+    printf("destructor for val2: %d\n", $$);
+} <val2>
+
+%destructor {
+    printf("destructor for expr: %d\n", $$);
+} expr // printer for symbol
+```
+
+Bison supports this feature from 1.75b.
+
+https://github.com/ruby/lrama/pull/385
+
 ## Lrama 0.6.3 (2024-02-15)
 
 ### Bring Your Own Stack
@@ -34,6 +98,8 @@ primary: k_if expr_value then compstmt if_tail k_end
           }
 ```
 
+https://github.com/ruby/lrama/pull/367
+
 ## Lrama 0.6.2 (2024-01-27)
 
 ### %no-stdlib directive
@@ -51,7 +117,7 @@ Allow to pass an instantiated rule to other parameterizing rules.
 
 ```
 %rule constant(X) : X
-              ;
+                  ;
 
 %rule option(Y) : /* empty */
                 | Y

tool/lrama/lib/lrama/grammar.rb

@@ -3,6 +3,7 @@
 require "lrama/grammar/binding"
 require "lrama/grammar/code"
 require "lrama/grammar/counter"
+require "lrama/grammar/destructor"
 require "lrama/grammar/error_token"
 require "lrama/grammar/parameterizing_rule"
 require "lrama/grammar/percent_code"
@@ -34,7 +35,7 @@ class Grammar
     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!
+                                        :fill_printer, :fill_destructor, :fill_error_token, :sort_by_number!
 
 
     def initialize(rule_counter)
@@ -43,6 +44,7 @@ def initialize(rule_counter)
       # Code defined by "%code"
       @percent_codes = []
       @printers = []
+      @destructors = []
       @error_tokens = []
       @symbols_resolver = Grammar::Symbols::Resolver.new
       @types = []
@@ -65,6 +67,10 @@ def add_percent_code(id:, code:)
       @percent_codes << PercentCode.new(id.s_value, code.s_value)
     end
 
+    def add_destructor(ident_or_tags:, token_code:, lineno:)
+      @destructors << Destructor.new(ident_or_tags: ident_or_tags, token_code: token_code, lineno: lineno)
+    end
+
     def add_printer(ident_or_tags:, token_code:, lineno:)
       @printers << Printer.new(ident_or_tags: ident_or_tags, token_code: token_code, lineno: lineno)
     end
@@ -345,6 +351,7 @@ def fill_symbols
       fill_symbol_number
       fill_nterm_type(@types)
       fill_printer(@printers)
+      fill_destructor(@destructors)
       fill_error_token(@error_tokens)
       sort_by_number!
     end

tool/lrama/lib/lrama/grammar/code.rb

@@ -1,4 +1,5 @@
 require "forwardable"
+require "lrama/grammar/code/destructor_code"
 require "lrama/grammar/code/initial_action_code"
 require "lrama/grammar/code/no_reference_code"
 require "lrama/grammar/code/printer_code"

tool/lrama/lib/lrama/grammar/code/destructor_code.rb

@@ -0,0 +1,40 @@
+module Lrama
+  class Grammar
+    class Code
+      class DestructorCode < Code
+        def initialize(type:, token_code:, tag:)
+          super(type: type, token_code: token_code)
+          @tag = tag
+        end
+
+        private
+
+        # * ($$) *yyvaluep
+        # * (@$) *yylocationp
+        # * ($:$) error
+        # * ($1) error
+        # * (@1) error
+        # * ($:1) error
+        def reference_to_c(ref)
+          case
+          when ref.type == :dollar && ref.name == "$" # $$
+            member = @tag.member
+            "((*yyvaluep).#{member})"
+          when ref.type == :at && ref.name == "$" # @$
+            "(*yylocationp)"
+          when ref.type == :index && ref.name == "$" # $:$
+            raise "$:#{ref.value} can not be used in #{type}."
+          when ref.type == :dollar # $n
+            raise "$#{ref.value} can not be used in #{type}."
+          when ref.type == :at # @n
+            raise "@#{ref.value} can not be used in #{type}."
+          when ref.type == :index # $:n
+            raise "$:#{ref.value} can not be used in #{type}."
+          else
+            raise "Unexpected. #{self}, #{ref}"
+          end
+        end
+      end
+    end
+  end
+end

tool/lrama/lib/lrama/grammar/destructor.rb

@@ -0,0 +1,9 @@
+module Lrama
+  class Grammar
+    class Destructor < Struct.new(:ident_or_tags, :token_code, :lineno, keyword_init: true)
+      def translated_code(tag)
+        Code::DestructorCode.new(type: :destructor, token_code: token_code, tag: tag).translated_code
+      end
+    end
+  end
+end

tool/lrama/lib/lrama/grammar/rule_builder.rb

@@ -115,12 +115,12 @@ def process_rhs(parameterizing_rule_resolver)
               @replaced_rhs << lhs_token
               parameterizing_rule_resolver.created_lhs_list << lhs_token
               parameterizing_rule.rhs_list.each do |r|
-                rule_builder = RuleBuilder.new(@rule_counter, @midrule_action_counter, i, lhs_tag: token.lhs_tag, skip_preprocess_references: true)
+                rule_builder = RuleBuilder.new(@rule_counter, @midrule_action_counter, lhs_tag: token.lhs_tag, skip_preprocess_references: true)
                 rule_builder.lhs = lhs_token
                 r.symbols.each { |sym| rule_builder.add_rhs(bindings.resolve_symbol(sym)) }
                 rule_builder.line = line
-                rule_builder.user_code = r.user_code
                 rule_builder.precedence_sym = r.precedence_sym
+                rule_builder.user_code = r.user_code
                 rule_builder.complete_input
                 rule_builder.setup_rules(parameterizing_rule_resolver)
                 @rule_builders_for_parameterizing_rules << rule_builder

tool/lrama/lib/lrama/grammar/stdlib.y

@@ -8,6 +8,9 @@
 
 **********************************************************************/
 
+// -------------------------------------------------------------------
+// Options
+
 /*
  * program: option(number)
  *
@@ -21,6 +24,45 @@
                | X
                ;
 
+// -------------------------------------------------------------------
+// Sequences
+
+/*
+ * program: preceded(opening, X)
+ *
+ * =>
+ *
+ * program: preceded_opening_X
+ * preceded_opening_X: opening X
+ */
+%rule preceded(opening, X): opening X { $$ = $2; }
+                          ;
+
+/*
+ * program: terminated(X, closing)
+ *
+ * =>
+ *
+ * program: terminated_X_closing
+ * terminated_X_closing: X closing
+ */
+%rule terminated(X, closing): X closing { $$ = $1; }
+                            ;
+
+/*
+ * program: delimited(opening, X, closing)
+ *
+ * =>
+ *
+ * program: delimited_opening_X_closing
+ * delimited_opening_X_closing: opening X closing
+ */
+%rule delimited(opening, X, closing): opening X closing { $$ = $2; }
+                                     ;
+
+// -------------------------------------------------------------------
+// Lists
+
 /*
  * program: list(number)
  *

tool/lrama/lib/lrama/grammar/symbol.rb

@@ -7,11 +7,12 @@
 module Lrama
   class Grammar
     class Symbol
-      attr_accessor :id, :alias_name, :tag, :number, :token_id, :nullable, :precedence, :printer, :error_token, :first_set, :first_set_bitmap
+      attr_accessor :id, :alias_name, :tag, :number, :token_id, :nullable, :precedence,
+                    :printer, :destructor, :error_token, :first_set, :first_set_bitmap
       attr_reader :term
       attr_writer :eof_symbol, :error_symbol, :undef_symbol, :accept_symbol
 
-      def initialize(id:, term:, alias_name: nil, number: nil, tag: nil, 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, destructor: nil)
         @id = id
         @alias_name = alias_name
         @number = number
@@ -21,6 +22,7 @@ def initialize(id:, term:, alias_name: nil, number: nil, tag: nil, token_id: nil
         @nullable = nullable
         @precedence = precedence
         @printer = printer
+        @destructor = destructor
       end
 
       def term?

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

@@ -58,7 +58,7 @@ def find_symbol_by_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}")
+          find_symbol_by_s_value(s_value) || (raise "Symbol not found. value: `#{s_value}`")
         end
 
         def find_symbol_by_id(id)
@@ -68,7 +68,7 @@ def find_symbol_by_id(id)
         end
 
         def find_symbol_by_id!(id)
-          find_symbol_by_id(id) || (raise "Symbol not found: #{id}")
+          find_symbol_by_id(id) || (raise "Symbol not found. #{id}")
         end
 
         def find_symbol_by_token_id(token_id)
@@ -78,7 +78,7 @@ def find_symbol_by_token_id(token_id)
         def find_symbol_by_number!(number)
           sym = symbols[number]
 
-          raise "Symbol not found: #{number}" unless sym
+          raise "Symbol not found. number: `#{number}`" unless sym
           raise "[BUG] Symbol number mismatch. #{number}, #{sym}" if sym.number != number
 
           sym
@@ -118,6 +118,23 @@ def fill_printer(printers)
           end
         end
 
+        def fill_destructor(destructors)
+          symbols.each do |sym|
+            destructors.each do |destructor|
+              destructor.ident_or_tags.each do |ident_or_tag|
+                case ident_or_tag
+                when Lrama::Lexer::Token::Ident
+                  sym.destructor = destructor if sym.id == ident_or_tag
+                when Lrama::Lexer::Token::Tag
+                  sym.destructor = destructor if sym.tag == ident_or_tag
+                else
+                  raise "Unknown token type. #{destructor}"
+                end
+              end
+            end
+          end
+        end
+
         def fill_error_token(error_tokens)
           symbols.each do |sym|
             error_tokens.each do |token|
@@ -154,7 +171,7 @@ def validate!
         def find_nterm_by_id!(id)
           @nterms.find do |s|
             s.id == id
-          end || (raise "Symbol not found: #{id}")
+          end || (raise "Symbol not found. #{id}")
         end
 
         def fill_terms_number

tool/lrama/lib/lrama/lexer.rb

@@ -21,6 +21,7 @@ class Lexer
       %define
       %require
       %printer
+      %destructor
       %lex-param
       %parse-param
       %initial-action

tool/lrama/lib/lrama/lexer/token.rb

@@ -18,7 +18,7 @@ def initialize(s_value:, alias_name: nil, location: nil)
       end
 
       def to_s
-        "#{super} location: #{location}"
+        "value: `#{s_value}`, location: #{location}"
       end
 
       def referred_by?(string)