rley 0.8.10 → 0.8.13

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 92dd793350853b0466c7d541d8e19bd5d03b661f6bc207836155968b8580584b
-  data.tar.gz: c1583a4668d945c55ab7b687748eec224adb16721a4fd108813abb61d4f3356a
+  metadata.gz: b1ad581d39b568b76013e43a7c1a04177845226c8d6a65cf49314a4897ad1e59
+  data.tar.gz: 6b626ec3a1f32e886a057075d90fc42fb07ddc0abe3a9d6abe357ccf934902dd
 SHA512:
-  metadata.gz: 948a5292ff798277c50e9a2b1829e9c0afb47886d7b1e4887409a98bcb08e490d493d3c672563b965f074756ce553f3a00c4729270a983f25b9b4a0389ab3505
-  data.tar.gz: d372ccc4cac0643c535759db3f63e2f5fa604dbc80fd72a85a9fb3f867b26a0a31d4a7e70925da0f2845f6e89d764efc886f5895ef1592798a13c76923839466
+  metadata.gz: 9185b89a40e09b17648415df3ade7d9a2948eee552e938d3452b0abc06082914cc48a4bd67ba389b36d9bf20c09ad42e3bf132487c8ce8d402687a2fa302d1d5
+  data.tar.gz: 5b2b5e1b4abf2f233e21edae90e2ee7a197b5bc9cedbaee5b2690b57562201e331dfff21b4115ffea48d5bd7086b9673cac2985aa9d7942fdac4d199ec1f43d9

data/.rubocop.yml

@@ -2,8 +2,8 @@ AllCops:
   Exclude:
     - 'exp/**/*'
 
-Gemspec/DateAssignment:
-  Enabled: true
+#Gemspec/DateAssignment:
+#  Enabled: true
 
 Gemspec/RequireMFA: # new in 1.23
   Enabled: false
@@ -133,6 +133,9 @@ Lint/RaiseException:
 
 Lint/RedundantDirGlobSort:
   Enabled: true
+  
+Lint/RefinementImportMethods: # new in 1.27
+  Enabled: true  
 
 Lint/RequireRelativeSelfPath:
   Enabled: true
@@ -328,6 +331,9 @@ Style/MultilineInPatternThen:
 
 Style/NegatedIfElseCondition:
   Enabled: true
+  
+Style/NestedFileDirname: # new in 1.26
+  Enabled: true
 
 Style/Next:
   Enabled: false
@@ -355,6 +361,9 @@ Style/RaiseArgs:
 
 Style/RedundantArgument:
   Enabled: true
+  
+Style/RedundantInitialize: # new in 1.27
+  Enabled: true  
 
 Style/RedundantReturn:
   Enabled: false

data/.yardopts

@@ -2,5 +2,5 @@
 --no-private
 --markup markdown
 -
-Changelog.md
-License.txt
+CHANGELOG.md
+LICENSE.txt

data/CHANGELOG.md

@@ -1,3 +1,17 @@
+### 0.8.13 / 2025-02-16
+- Tested against MRI Ruby 3.4.1.
+- [FIX] Fixed most "offenses" reported by Rubocop 1.72.0
+
+### 0.8.11 / 2022-04-17
+- Moved dependency on `prime` to gem.
+
+* [CHANGE] File `rley.gemspec` added runtime dependency on `prime` gem (rationale: was part of stdlib, from 3.1 it is demoted to a bundled gem)
+* [CHANGE] File `rgn\tokenizer.rb` minor style refactoring to please Rubocop 1.27
+
+### 0.8.10 / 2022-04-08
+- Refactoring of `RGN::Tokenizer` class.
+* [CHANGE] Class `RGN::Tokenizer` changes.
+
 ### 0.8.09 / 2022-01-28
 - Added code for coming tutorial
 

data/README.md

@@ -51,9 +51,9 @@ application range such as:
 
 ### Compatibility
 Rley supports the following Ruby implementations:
-- MRI 2.5
-- MRI 2.6 
-- MRI 2.7
+- MRI 3.2
+- MRI 3.3 
+- MRI 3.4
 - JRuby 9.1+  
 
 ---

data/examples/general/calc_iter2/calc_demo.rb

@@ -72,5 +72,5 @@ print_tree('Abstract Syntax Tree (AST)', ast_ptree)
 # Now perform the computation of math expression
 root = ast_ptree.root
 print_title('Result:')
-puts root.interpret.to_s # Output the expression result
+puts root.interpret # Output the expression result
 # End of file

data/examples/general/recursive_right.rb

@@ -0,0 +1,601 @@
+# frozen_string_literal: true
+
+require 'rley'
+
+# Simple right recursive grammar
+# based on example in D. Grune, C. Jacobs "Parsing Techniques" book
+# pp. 224 et sq.
+# S =>  a S;
+# S => ;
+# This grammar requires a time that is quadratic in the number of
+# input tokens
+# Similar grammar is also considered here: https://loup-vaillant.fr/tutorials/earley-parsing/right-recursion
+builder = Rley::grammar_builder do
+  # Define first the terminal symbols...
+  add_terminals('a')
+
+  # ... then with syntax rules
+  # First found rule is considered to be the top-level rule
+  rule('S' => 'a S')
+  rule('S' => [])
+end
+
+# Highly simplified tokenizer implementation.
+def tokenizer(aText, aGrammar)
+  index = 0
+  tokens = aText.scan(/a/).map do |letter_a|
+    terminal = aGrammar.name2symbol['a']
+    index += 1
+    pos = Rley::Lexical::Position.new(1, index)
+    Rley::Lexical::Token.new(letter_a, terminal, pos)
+  end
+
+  return tokens
+end
+
+right_recursive_grammar = builder.grammar.freeze
+
+
+input_to_parse = 'a' * 5
+
+parser = Rley::Parser::GFGEarleyParser.new(right_recursive_grammar)
+tokens = tokenizer(input_to_parse, right_recursive_grammar)
+result = parser.parse(tokens)
+
+# p result.chart.to_s
+
+
+# If we remove the .X and X. entries, then we have exactly the same output than Loup Vaillant
+
+=begin
+State[0]
+  .S | 0
+  S => . a S | 0
+  S => . | 0
+  S. | 0
+State[1]
+  S => a . S | 0
+  .S | 1
+  S => . a S | 1
+  S => . | 1
+  S. | 1
+  S => a S . | 0
+  S. | 0
+State[2]
+  S => a . S | 1
+  .S | 2
+  S => . a S | 2
+  S => . | 2
+  S. | 2
+  S => a S . | 1
+  S. | 1
+  S => a S . | 0
+  S. | 0
+State[3]
+  S => a . S | 2
+  .S | 3
+  S => . a S | 3
+  S => . | 3
+  S. | 3
+  S => a S . | 2
+  S. | 2
+  S => a S . | 1
+  S. | 1
+  S => a S . | 0
+  S. | 0
+State[4]
+  S => a . S | 3
+  .S | 4
+  S => . a S | 4
+  S => . | 4
+  S. | 4
+  S => a S . | 3
+  S. | 3
+  S => a S . | 2
+  S. | 2
+  S => a S . | 1
+  S. | 1
+  S => a S . | 0
+  S. | 0
+State[5]
+  S => a . S | 4
+  .S | 5
+  S => . a S | 5
+  S => . | 5
+  S. | 5
+  S => a S . | 4
+  S. | 4
+  S => a S . | 3
+  S. | 3
+  S => a S . | 2
+  S. | 2
+  S => a S . | 1
+  S. | 1
+  S => a S . | 0
+  S. | 0
+=end
+
+=begin
+from the right recursive grammar:
+  Terminals: a
+  Rules:
+    S => a S
+    S => []
+
+... the following table is generated:
+|               | .S | S. | (S -> .a S) |
+|:-------------:|:--:|:--:|-------------|
+|    .S start   |    | Ta |     Tb      |
+|    S. end     |    |    |             |
+|  (S -> .a S)  |    | Tc |     Td      |
+
+Two first rows are start and end nodes
+Remaining rows are for nodes with outgoing scan edge
+
+Algorithm to build the table
+start node
+end node
+find every scan edge
+
+=end
+
+
+def build_gfg(aGrammar)
+  items_builder = Object.new.extend(Rley::Base::GrmItemsBuilder)
+  items = items_builder.build_dotted_items(aGrammar)
+  gfg = Rley::GFG::GrmFlowGraph.new(items)
+end
+
+graph = build_gfg(right_recursive_grammar)
+
+=begin
+Execution simulation table construction
+Do a df traversal from start vertex
+  current_from: .S
+
+  Visit .S ; stack = [.S]
+
+  Visit S => .a S ; stack = [.S, S => . a S]
+    scan edge detected
+      table[.S] = {(S => . a S) => [[S => . a S]]}
+    current_from: (S => . a S)
+
+
+  Visit S => a . S; stack = [.S, S => . a S, S => a . S]
+    call edge to .S
+    current_from: (S => . a S)
+    prov_table[(S => . a S)] => { .S => [S => a . S] }
+
+  Visit .S; [.S, S => . a S, S => a . S, .S]
+    .S is a table heading
+    prov_table[(S => . a S)] => { .S => [S => a . S, .S] }
+    current_from: .S
+
+  Visit S => . ; stack = [.S, S => . a S, S => a . S, .S, S => .]
+    table[.S] = {..., S. => [[S => .]]}
+    current_from: .S
+
+  Visit S. ; stack = [.S, S => . a S, S => a . S, .S, S => ., S.]
+    S. is a table heading
+      table[.S] = {..., S. => [[S => ., S.]]}
+    current_from: S.
+
+  Visit S => a S .; stack = [.S, S => . a S, S => a . S, .S, S => ., S., S => a S .]
+    return edge to .S detected
+      table[S.] =  { S. => [[S => a S ., S.]]}
+
+  Visit S.; stack = [.S, S => . a S, S => a . S, .S, S => ., S., S => a S ., S.]
+    S. fully visited; pop it from stack
+
+  Visit S => a S .; stack = [.S, S => . a S, S => a . S, .S, S => ., S., S => a S .]
+    S => a S . fully visited; pop it from stack
+
+  Visit S.; stack = [.S, S => . a S, S => a . S, .S, S => ., S.]
+    S. fully visited; pop it from stack
+
+  Visit  S => .; stack = [.S, S => . a S, S => a . S, .S,  S => .]
+     S => . fully visited; pop it from stack
+
+  Visit .S; stack = [.S, S => . a S, S => a . S, .S]
+    .S fully visited; pop it from stack
+
+  Visit S => a . S; stack = [.S, S => . a S, S => a . S]
+    S => a . S fully visited; pop it from stack
+
+  Visit S => . a S; stack = [.S, S => . a S]
+    S => . a Sfully visited; pop it from stack
+
+  Visit .S; stack = [.S]
+    .S fully visited; pop it from stack
+
+  Stack contains couples of the type (node, node-from)
+  Stack empty; table is complete
+    table[.S] = {(S => . a S) => [[S => . a S, .S], S. => [[S => ., S.]]}
+    table[S.] =  { S. => [[S => a S ., S.]]}
+    prov_table[(S => . a S)] = { .S => [S => a . S] }
+    table[(S => . a S] = { (S => . a S) =>  [S => a . S, .S, S => . a S], S. =>[[S => a S ., S., S => ., S.]] }
+=end
+
+module GraphMixin
+  def build_table
+    table = { start_vertex => {} }
+    end_vertex = end_vertex_for[start_vertex.non_terminal]
+    table[end_vertex] = {}
+    term2scan_edge = {}
+
+    vertices.each do |vx|
+      next if vx.kind_of?(Rley::GFG::NonTerminalVertex)
+
+      edge = vx.edges[0]
+      next unless edge.kind_of?(Rley::GFG::ScanEdge)
+
+      table[edge] = {}
+      terminal = edge.terminal
+      term2scan_edge[terminal] = [] unless term2scan_edge.include? terminal
+      term2scan_edge[terminal] << edge
+    end
+
+    table
+  end
+
+  def build_raw_table
+    table = { start_vertex => {} }
+    end_vertex = end_vertex_for[start_vertex.non_terminal]
+    table[end_vertex] = {} # table: vertex => { to_vertex => [path to_vertex] }
+    visit = [start_vertex] # visit: stack of vertex to visit
+    from_indices = [0] # Array of indices. Each index refers to one visitee
+    vtx2count = { start_vertex => 0 }
+
+    loop do
+      break if visit.empty?
+
+      current_from = visit[from_indices.last]
+      visitee = visit.last
+      visit_count = vtx2count[visitee]
+      if visit_count < visitee.edges.size
+        # puts visitee.label
+        vtx2count[visitee] = visit_count + 1
+        edge = visitee.edges[visit_count]
+        # Do processing
+        if edge.kind_of?(Rley::GFG::ScanEdge) || ((visitee == start_vertex) && visit_count.positive?)
+          table[visitee] = {} unless table.include? visitee
+          current_row = table[current_from]
+          current_row[visitee] = [] unless current_row.include? visitee
+          current_row[visitee].concat(visit[from_indices.last..(visit.size - 1)])
+          from_indices << (visit.size - 1)
+        elsif (visitee == end_vertex) && visit_count.zero?
+          current_row = table[current_from]
+          current_row[visitee] = [] unless current_row.include? visitee
+          current_row[visitee].concat(visit[from_indices.last..(visit.size - 1)])
+          from_indices << (visit.size - 1)
+        end
+        successor = edge.successor
+        visit << successor
+        vtx2count[successor] = 0 unless vtx2count.include?(successor)
+      else
+        if (visitee == end_vertex) && visit_count == visitee.edges.size
+          current_row = table[current_from]
+          current_row[visitee] = [] unless current_row.include? visitee
+          slice = visit[from_indices.last..(visit.size - 1)]
+          if slice.size > 1
+            current_row[visitee].concat(slice)
+            from_indices << (visit.size - 1)
+          end
+        end
+        visit.pop
+        from_indices.pop if from_indices.last >= visit.size
+      end
+    end
+
+    table
+  end
+
+  def build_table2
+    raw_table = build_raw_table
+    refined_table = {}
+
+    # To get table right
+    # for every non start or end vertex:
+    # Check if there is an entry for start_vertex, if yes
+    # prefix path = raw_table[curr_vertex][start_vertex]
+    # remove last vertex in prefix path (it's start vertex)
+    # then for each entry from raw_table[start_vertex]:
+    #   create a keyval pair: key, value = prefix + original value
+    end_vertex = end_vertex_for[start_vertex.non_terminal]
+    raw_table.each_pair do |key, val|
+      if key == start_vertex || key == end_vertex
+        refined_table[key] = val.dup
+        next
+      end
+
+      if val.include? start_vertex
+        prefix_path = val[start_vertex]
+        prefix_path.pop
+        start_row = raw_table[start_vertex]
+        new_row = val.dup
+        new_row.delete(start_vertex)
+        start_row.each_pair do |to_vertex, to_path|
+          new_row[to_vertex] = prefix_path + to_path
+        end
+        refined_table[key] = new_row
+      end
+    end
+
+    refined_table
+  end
+
+  # visit_action takes two arguments: a vertex and an edge
+  # return true/false if false stop traversal
+  def df_traversal(aVertex, &visit_action)
+    visit = [aVertex]
+    vtx2count = { aVertex => 0 }
+
+    loop do
+      break if visit.empty?
+
+      visitee = visit.last
+      visit_count = vtx2count[visitee]
+      if visit_count < visitee.edges.size
+        # puts visitee.label
+        vtx2count[visitee] = visit_count + 1
+        edge = visitee.edges[visit_count]
+        resume = block_given? ? yield(visitee, edge) : true
+        if resume
+          successor = edge.successor
+          visit << successor
+          vtx2count[successor] = 0 unless vtx2count.include?(successor)
+        end
+      else
+        visit.pop
+      end
+    end
+  end
+
+  def row_to_s(aRow)
+    result = +''
+    aRow.each_pair do |to_vertex, to_path|
+      path_text = to_path.map(&:label).join(', ')
+      result << "#{to_vertex.label} => [#{path_text}]\n"
+    end
+
+    result
+  end
+end # module
+
+graph.extend(GraphMixin)
+# graph.df_traversal(graph.start_vertex) { |n, _edge|  puts n.label; true }
+# p graph.build_table.size
+raw_table = graph.build_raw_table
+p raw_table[graph.start_vertex]
+# (S. => .a S) => [.S, S => .a S], S. => [.S, S => ., S.]
+
+p raw_table[raw_table.keys[1]]
+# S. => [S., S=> a S., S.]
+
+p raw_table[raw_table.keys[2]]
+# .S => [S => .a S, S => a .S, .S]
+
+# raw_table[.S] = { (S. => .a S) => [.S, S => .a S], S. => [.S, S => ., S.] }
+# raw_table[.S] = { S. => [S., S=> a S., S.] }
+# raw_table[S => .a S] = { .S => [S => .a S, S => a .S, .S] }
+
+refined_table = graph.build_table2
+puts '=='
+puts graph.row_to_s(refined_table[graph.start_vertex])
+# refined_table[start_vertex] = { (S => .a S) => [.S, S => .a S], S. => [S., S => ., S.] }
+puts '=='
+puts graph.row_to_s(refined_table[refined_table.keys[1]])
+# refined_table[S.] = { S. => [S., S => a S., S.] }
+puts '=='
+puts graph.row_to_s(refined_table[refined_table.keys[2]])
+# refined_table[S => .a S] = { (S => .a S) => [S => .a S, S => a .S, .S, S -> .a S],
+#                              S. => [S => .a S, S => a .S, .S, S => ., S.]  }
+
+
+# |               | .S | S. | (S -> .a S) |
+# |:-------------:|:--:|:--:|-------------|
+# |    .S start   |    | Ta |     Tb      |
+# |    S. end     |    | ?? |             |
+# |  (S -> .a S)  |    | Tc |     Td      |
+
+
+class TransitionTable
+  attr_reader(:table)
+
+  def initialize(aTable)
+    @table = aTable
+  end
+
+  def paths_from_start(aTerminalName)
+    destinations = table.values.first
+    result = []
+    destinations.each_pair do |to_vx, path|
+      next unless Rley::GFG::ItemVertex
+
+      result << path if to_vx.next_symbol&.name == aTerminalName
+    end
+
+    result
+  end
+
+  def paths_from(from_terminal, to_terminal)
+    from_vertices = table.keys.select do |vx|
+      vx.kind_of?(Rley::GFG::ItemVertex) && vx.next_symbol&.name == from_terminal
+    end
+
+    result = []
+    from_vertices.each do |fr_vx|
+      destinations = table[fr_vx]
+      destinations.each_pair do |to_vx, path|
+        next unless Rley::GFG::ItemVertex
+
+        result << path if to_vx.next_symbol&.name == to_terminal
+      end
+    end
+
+    result
+  end
+
+  def paths_to_end(from_terminal)
+    from_vertices = table.keys.select do |vx|
+      vx.kind_of?(Rley::GFG::ItemVertex) && vx.next_symbol&.name == from_terminal
+    end
+
+    result = []
+    from_vertices.each do |fr_vx|
+      destinations = table[fr_vx]
+      destinations.each_pair do |to_vx, path|
+        result << path if to_vx.kind_of?(Rley::GFG::EndVertex)
+      end
+    end
+
+    result
+  end
+end # class
+
+=begin
+  Simulation of recognizer algorithm
+  input: aaaaa
+  Reminder:
+  # refined_table[start_vertex] = { (S => .a S) => [.S, S => .a S], S. => [S., S => ., S.] }
+  # refined_table[S.] = { S. => [S., S => a S., S.] }
+  # refined_table[S => .a S] = { (S => .a S) => [S => .a S, S => a .S, .S, S -> .a S],
+  #                              S. => [S => .a S, S => a .S, .S, S => ., S.]  }
+
+  Maybe one needs to transform the above table into terminal => terminal table
+
+  Computing state 0
+    What is next terminal? a
+    We push P1 == (S => .a S) => [.S, S => .a S]
+
+  Computing state 1
+    What is next terminal? a
+    We push P2 == (S => .a S) => [S => .a S, S => a .S, .S, S -> .a S]
+
+  Computing state 2
+    What is next terminal? a
+    We push P2 == (S => .a S) => [S => .a S, S => a .S, .S, S -> .a S]
+
+  Computing state 3
+    What is next terminal? a
+    We push P2 == (S => .a S) => [S => .a S, S => a .S, .S, S -> .a S]
+
+  Computing state 4
+    What is next terminal? a
+    We push P2 == (S => .a S) => [S => .a S, S => a .S, .S, S -> .a S]
+
+  Computing state 5
+    What is next terminal? EOS
+     We push P3 == S. => [S => .a S, S => a .S, .S, S => ., S.]
+
+  Recognizer terminates here.
+=end
+
+class Recognizer
+  attr_reader(:table)
+
+  def initialize(aTable)
+    @table = TransitionTable.new(aTable)
+  end
+
+  # @param enumerator [Enumerator] Enumerator that yields Terminal symbols
+  def run(enum_tokens)
+    states = []
+    prev_terminal = nil
+    paths = nil
+    enum_tokens.each_with_index do |token, index|
+      terminal_name = token.terminal.name
+      if index.zero?
+        paths = table.paths_from_start(terminal_name)
+      else
+        paths = table.paths_from(prev_terminal, terminal_name)
+      end
+      prev_terminal = terminal_name
+      raise StandardError, "Error at position #{index} with #{token.lexeme}." if paths.empty?
+
+      states << paths
+    end
+
+    paths = table.paths_to_end(prev_terminal)
+    raise StandardError, "Error at position #{index} with #{token.lexeme}." if paths.empty?
+
+    states << paths
+
+    states
+  end
+end # class
+
+
+recog = Recognizer.new(refined_table)
+states = recog.run(tokens)
+puts 'Done!'
+p states[5]
+# states[0] = [[.S, S => .a S]]
+# states[1] = [[S => .a S, S => a .S, .S, S => .a S]]
+# states[4] = [[S => .a S, S => a .S, .S, S => .a S]]
+# states[5] = [[S => .a S, S => a .S, .S, S => a S., S.]]
+
+# Simulation for second recognizer pass
+# Every entry edge has an identifier
+# Corresponding exit edge has same identifier negated
+# Call and return edges are ambiguous when a non-terminal is lhs of multiple productions
+# Creating statechart[0]:
+# for each path do
+#   for each item vertex do
+#     push on current statechart rank, the item vertices
+#  statechart[0] # next token is 'a'.  There is only one path from .S to S => .a S
+#    push S => .a S @ 0
+#    stack:
+#      S => .a S @ 0
+
+#  statechart[1] # next to token is 'a'. There is only one path from S => a .S to S => .a S
+#    Remove vertex from previous state
+#    push S => a . S @ 0
+#    push S => .a S @ 1 # Start vertex discarded
+#    stack:
+#      S => .a S @ 1
+#      S => .a S @ 0
+#
+#  statechart[2] # next to token is 'a'. There is only one path from S => a .S to S => .a S
+#    Remove vertex from previous state
+#    push S => a . S @ 1
+#    push S => .a S @ 2 # Start vertex discarded
+#    stack:
+#      S => .a S @ 2
+#      S => .a S @ 1
+#      S => .a S @ 0
+#
+#  statechart[3] # next to token is 'a'. There is only one path from S => a .S to S => .a S
+#    Remove vertex from previous state
+#    push S => a . S @ 2
+#    push S => .a S @ 3 # Start vertex discarded
+#    stack:
+#      S => .a S @ 3
+#      S => .a S @ 2
+#      S => .a S @ 1
+#      S => .a S @ 0
+#
+#  statechart[4] # next to token is 'a'. There is only one path from S => a .S to S => .a S
+#    Remove vertex from previous state
+#    push S => a . S @ 3
+#    push S => .a S @ 4 # Start vertex discarded
+#    stack:
+#      S => .a S @ 4
+#      S => .a S @ 3
+#      S => .a S @ 2
+#      S => .a S @ 1
+#      S => .a S @ 0
+#
+#  statechart[5] # next to token is EOS. There is only one path from S => a .S to S.
+#    Remove vertex from previous state
+#    push S => a . S @ 4
+#    push .S  @ 5 ?
+#    push S => . @5
+#    push S. possibly add 0..n events S => a S. @ xx
+#    stack:
+#      S => .a S @ 4 expecting S => a S @ 4 event
+#      S => .a S @ 3
+#      S => .a S @ 2
+#      S => .a S @ 1
+#      S => .a S @ 0
+#

data/examples/tokenizer/loxxy_raw_scanner.rex

@@ -1,14 +1,17 @@
-# As Rubocop shouts about "offences" in the generated code, 
+# As Rubocop shouts about "offences" in the generated code,
 # we disable the detection of most of them...
 # rubocop: disable Style/MutableConstant
 # rubocop: disable Layout/SpaceBeforeSemicolon
 # rubocop: disable Style/Alias
 # rubocop: disable Style/AndOr
 # rubocop: disable Style/MultilineIfModifier
+# rubocop: disable Style/MultilineIfThen
 # rubocop: disable Style/StringLiterals
 # rubocop: disable Style/MethodDefParentheses
-# rubocop: disable Security/Open
+# rubocop: disable Style/RedundantParentheses
+# rubocop: disable Style/SlicingWithRange
 # rubocop: disable Style/TrailingCommaInArrayLiteral
+# rubocop: disable Security/Open#
 # rubocop: disable Layout/EmptyLinesAroundMethodBody
 # rubocop: disable Style/WhileUntilDo
 # rubocop: disable Style/MultilineWhenThen
@@ -94,6 +97,9 @@ end
 # rubocop: enable Style/MultilineIfModifier
 # rubocop: enable Style/StringLiterals
 # rubocop: enable Style/MethodDefParentheses
+# rubocop: enable Style/MultilineIfThen:
+# rubocop: enable Style/RedundantParentheses
+# rubocop: enable Style/SlicingWithRange
 # rubocop: enable Security/Open
 # rubocop: enable Style/TrailingCommaInArrayLiteral
 # rubocop: enable Layout/EmptyLinesAroundMethodBody

data/examples/tokenizer/loxxy_raw_scanner.rex.rb

@@ -1,10 +1,8 @@
 # frozen_string_literal: true
 
-# encoding: UTF-8
-
 #--
 # This file is automatically generated. Do not modify it.
-# Generated by: oedipus_lex version 2.5.3.
+# Generated by: oedipus_lex version 2.6.2.
 # Source: loxxy_raw_scanner.rex
 #++
 
@@ -15,10 +13,13 @@
 # rubocop: disable Style/Alias
 # rubocop: disable Style/AndOr
 # rubocop: disable Style/MultilineIfModifier
+# rubocop: disable Style/MultilineIfThen
 # rubocop: disable Style/StringLiterals
 # rubocop: disable Style/MethodDefParentheses
-# rubocop: disable Security/Open
+# rubocop: disable Style/RedundantParentheses
+# rubocop: disable Style/SlicingWithRange
 # rubocop: disable Style/TrailingCommaInArrayLiteral
+# rubocop: disable Security/Open#
 # rubocop: disable Layout/EmptyLinesAroundMethodBody
 # rubocop: disable Style/WhileUntilDo
 # rubocop: disable Style/MultilineWhenThen
@@ -104,7 +105,6 @@ class LoxxyRawScanner
     old_pos - start_of_current_line_pos
   end
 
-
   ##
   # The current scanner class. Must be overridden in subclasses.
 
@@ -153,7 +153,7 @@ class LoxxyRawScanner
     token = nil
 
     until ss.eos? or token do
-      if ss.peek(1) == "\n"
+      if ss.check(/\n/) then
         self.lineno += 1
         # line starts 1 position after the newline
         self.start_of_current_line_pos = ss.pos + 1
@@ -246,6 +246,9 @@ end # class
   # rubocop: enable Style/MultilineIfModifier
   # rubocop: enable Style/StringLiterals
   # rubocop: enable Style/MethodDefParentheses
+  # rubocop: enable Style/MultilineIfThen:
+  # rubocop: enable Style/RedundantParentheses
+  # rubocop: enable Style/SlicingWithRange
   # rubocop: enable Security/Open
   # rubocop: enable Style/TrailingCommaInArrayLiteral
   # rubocop: enable Layout/EmptyLinesAroundMethodBody

data/examples/tokenizer/loxxy_tokenizer.rb

@@ -23,7 +23,7 @@ class LoxxyTokenizer
     lookup = %w[
       and class else false fun for if nil or
       print return super this true var while
-    ].map { |x| [x, x.upcase] }.to_h
+    ].to_h { |x| [x, x.upcase] }
     lookup.default = 'IDENTIFIER'
     lookup.freeze
   end

data/lib/rley/constants.rb

@@ -5,7 +5,7 @@
 
 module Rley # Module used as a namespace
   # The version number of the gem.
-  Version = '0.8.10'
+  Version = '0.8.13'
 
   # Brief description of the gem.
   Description = "Ruby implementation of the Earley's parsing algorithm"

data/lib/rley/engine.rb

@@ -80,9 +80,11 @@ module Rley # This module is used as a namespace
       aTokenizer.each do |a_token|
         next unless a_token
 
-        term_name = a_token.terminal
-        term_symb = grammar.name2symbol[term_name]
-        a_token.instance_variable_set(:@terminal, term_symb)
+        if a_token.terminal.kind_of?(String)
+          term_name = a_token.terminal
+          term_symb = grammar.name2symbol[term_name]
+          a_token.instance_variable_set(:@terminal, term_symb)
+        end
         tokens << a_token
       end
       parser = build_parser(grammar)

data/lib/rley/rgn/grammar_builder.rb

@@ -386,23 +386,6 @@ module Rley # This module is used as a namespace
         end
       end
 
-      # def sequence_name(aSequenceNode)
-      #   subnode_names = +''
-      #   aSequenceNode.subnodes.each do |subn|
-      #     case subn
-      #     when SymbolNode
-      #       subnode_names << "_#{subn.name}"
-      #     when SequenceNode
-      #       subnode_names << "_#{sequence_name(subn)}"
-      #     when RepetitionNode
-      #       suffix = repetition2suffix(subn.repetition)
-      #       subnode_names << suffix
-      #     end
-      #   end
-      #
-      #   "seq#{subnode_names}"
-      # end
-
       def node_base_name(aNode)
         if aNode.kind_of?(SymbolNode)
           aNode.name
@@ -418,24 +401,6 @@ module Rley # This module is used as a namespace
         "#{base_name}#{suffix}"
       end
 
-      # def serialize_sequence(aSequenceNode)
-      #   text = +''
-      #   aSequenceNode.subnodes.each do |sn|
-      #     text << ' '
-      #     case sn
-      #     when SymbolNode
-      #       text << sn.name
-      #     when SequenceNode
-      #       text << sequence_name(sn)
-      #     when RepetitionNode
-      #       suffix = repetition2suffix(sn.repetition)
-      #       text << suffix
-      #     end
-      #   end
-      #
-      #   text.strip
-      # end
-
       def add_raw_rule(aSymbol, aRHS, aTag, simplified = false, constraints = [])
         raw_rule = RawRule.new(aSymbol, aRHS, aTag, simplified, constraints)
         if synthetized.include?(aSymbol)

data/lib/rley/rgn/tokenizer.rb

@@ -46,7 +46,7 @@ module Rley
       # Here are all the implemented Rley notation keywords
       @@keywords = %w[
         match_closest repeat
-      ].map { |x| [x, x] }.to_h
+      ].to_h { |x| [x, x] }
 
       # Constructor. Initialize a tokenizer for RGN input.
       # @param source [String] RGN text to tokenize.
@@ -129,10 +129,7 @@ module Rley
           ws_found = false
         end # until
 
-        # unterminated(@string_start.line, @string_start.column) if state == :multiline
         token
-
-        # return token
       end
 
       def build_token(aSymbolName, aLexeme)

data/spec/rley/parser/dangling_else_spec.rb

@@ -49,7 +49,7 @@ module Rley # Open this namespace to avoid module qualifier prefixes
               term_name = 'INTEGER'
             else
               err_msg = "Unknown token '#{lexeme}'"
-              raise StandardError,  err_msg
+              raise StandardError, err_msg
             end
           end
           pos = Rley::Lexical::Position.new(1, curr_pos + 1)

data/spec/rley/parser/gfg_earley_parser_spec.rb

@@ -104,9 +104,9 @@ module Rley # Open this namespace to avoid module qualifier prefixes
       context 'Parsing: ' do
         # rubocop: disable Naming/VariableNumber
         it 'should parse a valid simple input' do
-          parse_result = subject.parse(grm1_tokens)
+          parse_result = subject.parse(build_token_sequence(%w[a a b c c], grammar_abc))
           expect(parse_result.success?).to eq(true)
-          # expect(parse_result.ambiguous?).to eq(false)
+          expect(parse_result.ambiguous?).to eq(false)
           ######################
           # Expectation chart[0]:
           expected = [

data/spec/spec_helper.rb

@@ -3,7 +3,6 @@
 # File: spec_helper.rb
 # Purpose: utility file that is loaded by all our RSpec files
 
-require 'pp'    # Use pretty-print for debugging purposes
 require 'rspec' # Use the RSpec framework
 
 

metadata

@@ -1,75 +1,88 @@
 --- !ruby/object:Gem::Specification
 name: rley
 version: !ruby/object:Gem::Version
-  version: 0.8.10
+  version: 0.8.13
 platform: ruby
 authors:
 - Dimitri Geshef
-autorequire:
 bindir: bin
 cert_chain: []
-date: 2022-04-08 00:00:00.000000000 Z
+date: 2025-02-16 00:00:00.000000000 Z
 dependencies:
+- !ruby/object:Gem::Dependency
+  name: prime
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.1.2
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.1.2
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '13.0'
+        version: 13.1.0
     - - ">="
       - !ruby/object:Gem::Version
-        version: 13.0.0
+        version: 13.1.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '13.0'
+        version: 13.1.0
     - - ">="
       - !ruby/object:Gem::Version
-        version: 13.0.0
+        version: 13.1.0
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.5'
+        version: 3.12.0
     - - ">="
       - !ruby/object:Gem::Version
-        version: 3.5.0
+        version: 3.12.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.5'
+        version: 3.12.0
     - - ">="
       - !ruby/object:Gem::Version
-        version: 3.5.0
+        version: 3.12.0
 - !ruby/object:Gem::Dependency
-  name: rubygems
+  name: yard
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: 0.9.34
     - - ">="
       - !ruby/object:Gem::Version
-        version: 2.0.0
+        version: 0.9.34
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: 0.9.34
     - - ">="
       - !ruby/object:Gem::Version
-        version: 2.0.0
+        version: 0.9.34
 description: A general parser using the Earley algorithm.
 email: famished.tiger@yahoo.com
 executables: []
@@ -80,7 +93,6 @@ files:
 - ".rspec"
 - ".rubocop.yml"
 - ".ruby-gemset"
-- ".travis.yml"
 - ".yardopts"
 - CHANGELOG.md
 - LICENSE.txt
@@ -122,6 +134,7 @@ files:
 - examples/general/calc_iter2/spec/calculator_spec.rb
 - examples/general/general_examples.md
 - examples/general/left.rb
+- examples/general/recursive_right.rb
 - examples/general/right.rb
 - examples/tokenizer/README.md
 - examples/tokenizer/loxxy_raw_scanner.rex
@@ -296,15 +309,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 2.5.0
+      version: 3.2.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.3
-signing_key:
+rubygems_version: 3.6.2
 specification_version: 4
 summary: Ruby implementation of the Earley's parsing algorithm
 test_files:

data/.travis.yml

@@ -1,29 +0,0 @@
-language: ruby
-dist: trusty
-
-before_install:
-  - gem update --system
-  - gem install bundler  
-
-script:
-  - bundle exec rake
-  
-rvm:
-  - 2.7.1
-  - 2.6.6
-  - 2.5.8
-  - 2.4.10
-  - ruby-head
-  - jruby-head 
-before_install: gem install bundler -v 2.0.2  
-  
-matrix:
-  allow_failures:
-    - rvm: ruby-head
-    - rvm: jruby-head
-
-
-# whitelist
-branches:
-  only:
-    - master