rley 0.3.09 → 0.3.10

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: d22d11b51c4c72d3d8230c775b797afae04c4e8f
-  data.tar.gz: e87ba3a3beeadd40a4447281c904f8dba4c8dc57
+  metadata.gz: 20ceec50ffa7359dbf635a00184c604654cdf9bb
+  data.tar.gz: 76e9432f62d88127257c66277e21be37fd1b00bd
 SHA512:
-  metadata.gz: 446344010aafea29682d90bd71bdb73f1f189e694fb91907136e00cce015b098e32fb2679af3a0b6ae772d41892478b0a9270c43ebe77cee2c47cb319b7fd0aa
-  data.tar.gz: 9509ea071e10c002e70af379089565b3b28269fb09c1f1d04ee9a04ec78dab7ac916e4f90602bbef5bc3eff8ea0952143faa5ec1d6c54277b60e7db810dab45d
+  metadata.gz: a80c8e38ede7dd3908a52b73fd8fa13fc7087537d8272c8d648764902cb29f0d5db23c157a2b704eb66e2c8322d7e2ee4822dfd36fadb25ac22e6ec9f517f3eb
+  data.tar.gz: 9d23a806c510790c6fcc19566520e11c9292d642b2debe20784c4a884d646c173a789ae3060345ad659698554fce6748078ef7d5cc2353f7e1c3495ecd156104

data/CHANGELOG.md

@@ -1,3 +1,12 @@
+### 0.3.10 / 2016-12-04
+* [NEW] Method `ParseForest#ambiguous?`. Indicates whether the parse is ambiguous.
+* [CHANGE] File `README.md` updated with new grammar builder syntax & typo fixes.
+* [CHANGE] Method `GrammarBuilder#initialize`: Accepts a block argument that allows lighter construction.
+
+### 0.3.09 / 2016-11-27
+* [CHANGE] File `README.md` fully rewritten and added an example.
+* [CHANGE] Directory `examples` completely reorganized.
+
 ### 0.3.09 / 2016-11-27
 * [CHANGE] File `README.md` fully rewritten and added an example.
 * [CHANGE] Directory `examples` completely reorganized.

data/README.md

@@ -9,7 +9,7 @@
 [Rley](https://github.com/famished-tiger/Rley)
 ======
 
-A Ruby library for constructing general parsers for _any_ context-free languages.  
+A Ruby library for constructing general parsers for _any_ context-free language.  
 
 
 What is Rley?
@@ -69,7 +69,7 @@ The tour is organized into the following steps:
 1. [Defining the language grammar](#defining-the-language-grammar)  
 2. [Creating a lexicon](#creating-a-lexicon)  
 3. [Creating a tokenizer](#creating-a-tokenizer)  
-4. [Building the parser](building-the-parser)  
+4. [Building the parser](#building-the-parser)  
 5. [Parsing some input](#parsing-some-input)  
 6. [Generating the parse forest](#generating-the-parse-forest)
 
@@ -84,21 +84,20 @@ The subset of English grammar is based on an example from the NLTK book.
     require 'rley'  # Load Rley library
 
     # Instantiate a builder object that will build the grammar for us
-    builder = Rley::Syntax::GrammarBuilder.new
-
-    # Next 2 lines we define the terminal symbols (=word categories in the lexicon)
-    builder.add_terminals('Noun', 'Proper-Noun', 'Verb')
-    builder.add_terminals('Determiner', 'Preposition')
-
-    # Here we define the productions (= grammar rules)
-    builder.add_production('S' => %w[NP VP])
-    builder.add_production('NP' => 'Proper-Noun')
-    builder.add_production('NP' => %w[Determiner Noun])
-    builder.add_production('NP' => %w[Determiner Noun PP])
-    builder.add_production('VP' => %w[Verb NP])
-    builder.add_production('VP' => %w[Verb NP PP])
-    builder.add_production('PP' => %w[Preposition NP])
-
+    builder = Rley::Syntax::GrammarBuilder.new do
+      # Terminal symbols (= word categories in lexicon)
+      add_terminals('Noun', 'Proper-Noun', 'Verb') 
+      add_terminals('Determiner', 'Preposition')
+
+      # Here we define the productions (= grammar rules)
+      rule 'S' => %w[NP VP]
+      rule 'NP' => 'Proper-Noun'
+      rule 'NP' => %w[Determiner Noun]
+      rule 'NP' => %w[Determiner Noun PP]
+      rule 'VP' => %w[Verb NP]
+      rule 'VP' => %w[Verb NP PP]
+      rule 'PP' => %w[Preposition NP]
+    end 
     # And now, let's build the grammar...
     grammar = builder.grammar
 ```  
@@ -208,8 +207,6 @@ Here are a few other ones:
 ##  Thanks to:
 * Professor Keshav Pingali, one of the creators of the Grammar Flow Graph parsing approach for his encouraging e-mail exchanges.
 
----
-
 Copyright
 ---------
 Copyright (c) 2014-2016, Dimitri Geshef.  

data/examples/NLP/mini_en_demo.rb

@@ -9,20 +9,20 @@ require 'rley'  # Load Rley library
 # with a very simplified syntax.
 
 # Instantiate a builder object that will build the grammar for us
-builder = Rley::Syntax::GrammarBuilder.new
+builder = Rley::Syntax::GrammarBuilder.new do
+  # Next 2 lines we define the terminal symbols (=word categories in the lexicon)
+  add_terminals('Noun', 'Proper-Noun', 'Verb') 
+  add_terminals('Determiner', 'Preposition')
 
-# Next 2 lines we define the terminal symbols (=word categories in the lexicon)
-builder.add_terminals('Noun', 'Proper-Noun', 'Verb') 
-builder.add_terminals('Determiner', 'Preposition')
-
-# Here we define the productions (= grammar rules)
-builder.add_production('S' => %w[NP VP])
-builder.add_production('NP' => 'Proper-Noun')
-builder.add_production('NP' => %w[Determiner Noun])
-builder.add_production('NP' => %w[Determiner Noun PP])
-builder.add_production('VP' => %w[Verb NP])
-builder.add_production('VP' => %w[Verb NP PP])
-builder.add_production('PP' => %w[Preposition NP])
+  # Here we define the productions (= grammar rules)
+  rule 'S' => %w[NP VP]
+  rule 'NP' => 'Proper-Noun'
+  rule 'NP' => %w[Determiner Noun]
+  rule 'NP' => %w[Determiner Noun PP]
+  rule 'VP' => %w[Verb NP]
+  rule 'VP' => %w[Verb NP PP]
+  rule 'PP' => %w[Preposition NP]
+end 
 
 # And now, let's build the grammar...
 grammar = builder.grammar
@@ -70,8 +70,6 @@ def tokenizer(aTextToParse, aGrammar)
   return tokens
 end
 
-More realistic NLP will will most probably
-
 ########################################
 # Step 4. Create a parser for that grammar
 # Easy with Rley...
@@ -80,6 +78,7 @@ parser = Rley::Parser::GFGEarleyParser.new(grammar)
 ########################################
 # Step 5. Parsing the input
 input_to_parse = 'John saw Mary with a telescope'
+# input_to_parse = 'the dog saw a man in the park' # This one is ambiguous
 # Convert input text into a sequence of token objects...
 tokens = tokenizer(input_to_parse, grammar)
 result = parser.parse(tokens)
@@ -90,3 +89,4 @@ puts "Parsing successful? #{result.success?}" # => Parsing successful? true
 # Step 6. Generating the parse forest
 pforest = result.parse_forest
 
+puts "Parsing ambiguous? #{pforest.ambiguous?}" # => Parsing ambiguous? false

data/lib/rley/constants.rb

@@ -3,7 +3,7 @@
 
 module Rley # Module used as a namespace
   # The version number of the gem.
-  Version = '0.3.09'.freeze
+  Version = '0.3.10'.freeze
 
   # Brief description of the gem.
   Description = "Ruby implementation of the Earley's parsing algorithm".freeze

data/lib/rley/parser/parse_forest_builder.rb

@@ -29,7 +29,7 @@ module Rley # This module is used as a namespace
       # A hash with pairs of the form: visited parse entry => forest node
       attr_reader(:entry2node)
 
-      # A hash with pairs of the form: 
+      # A hash with pairs of the form:
       # parent end entry => path to alternative node
       # This is needed for synchronizing backtracking
       attr_reader(:entry2path_to_alt)
@@ -89,12 +89,12 @@ module Rley # This module is used as a namespace
 
 
           when :revisit
-            # Retrieve the already existing node corresponding 
+            # Retrieve the already existing node corresponding
             # to re-visited entry
             popular = @entry2node[anEntry]
-            
+
             # Share with parent (if needed)...
-            children = curr_parent.subnodes            
+            children = curr_parent.subnodes
             curr_parent.add_subnode(popular) unless children.include? popular
 
           else
@@ -105,7 +105,7 @@ module Rley # This module is used as a namespace
 
       def process_item_entry(anEvent, anEntry, anIndex)
         case anEvent
-          when :visit      
+          when :visit
             if anEntry.exit_entry?
               # Previous entry was an end entry (X. pattern)
               # Does the previous entry have multiple antecedent?
@@ -119,7 +119,7 @@ module Rley # This module is used as a namespace
                 create_alternative_node(anEntry)
               end
             end
-            
+
             # Does this entry have multiple antecedent?
             if anEntry.antecedents.size > 1
               # Store current path for later backtracking
@@ -129,7 +129,7 @@ module Rley # This module is used as a namespace
               # curr_parent.refinement = :or
 
               create_alternative_node(anEntry)
-            end      
+            end
 
             # Retrieve the grammar symbol before the dot (if any)
             prev_symbol = anEntry.prev_symbol
@@ -146,7 +146,7 @@ module Rley # This module is used as a namespace
                 end
                 curr_path.pop if curr_parent.kind_of?(SPPF::AlternativeNode)
             end
-            
+
           when :backtrack
             # Restore path
             @curr_path = entry2path_to_alt[anEntry].dup
@@ -154,9 +154,9 @@ module Rley # This module is used as a namespace
             antecedent_index = curr_parent.subnodes.size
             # puts "Current parent #{curr_parent.to_string(0)}"
             # puts "Antecedent index #{antecedent_index}"
-            
-            create_alternative_node(anEntry)            
-            
+
+            create_alternative_node(anEntry)
+
         when :revisit
             # Retrieve the grammar symbol before the dot (if any)
             prev_symbol = anEntry.prev_symbol
@@ -172,7 +172,7 @@ module Rley # This module is used as a namespace
                   create_epsilon_node(anEntry, anIndex)
                 end
                 curr_path.pop if curr_parent.kind_of?(SPPF::AlternativeNode)
-            end        
+            end
         end
       end
 
@@ -187,8 +187,8 @@ module Rley # This module is used as a namespace
         non_terminal = nonTSymb.nil? ? anEntry.vertex.non_terminal : nonTSymb
         new_node = Rley::SPPF::NonTerminalNode.new(non_terminal, aRange)
         entry2node[anEntry] = new_node
-        # puts "FOREST ADD #{curr_parent.key if curr_parent}/#{new_node.key}"
         add_subnode(new_node)
+        # puts "FOREST ADD #{curr_parent.key if curr_parent}/#{new_node.key}"
 
         return new_node
       end
@@ -200,6 +200,7 @@ module Rley # This module is used as a namespace
         range = curr_parent.range
         alternative = Rley::SPPF::AlternativeNode.new(vertex, range)
         add_subnode(alternative)
+        forest.is_ambiguous = true
         # puts "FOREST ADD #{alternative.key}"
 
         return alternative
@@ -231,13 +232,13 @@ module Rley # This module is used as a namespace
       # Add the given node if not yet present in parse forest
       def add_node_to_forest(aNode)
         key_node = aNode.key
-        if forest.include?(key_node)
-          new_node = forest.key2node[key_node]
-        else
-          new_node = aNode
-          forest.key2node[key_node] = new_node
-          # puts "FOREST ADD #{key_node}"
-        end
+          if forest.include?(key_node)
+            new_node = forest.key2node[key_node]
+          else
+            new_node = aNode
+            forest.key2node[key_node] = new_node
+            # puts "FOREST ADD #{key_node}"
+          end
         add_subnode(new_node, false)
 
         return new_node

data/lib/rley/sppf/parse_forest.rb

@@ -1,5 +1,6 @@
 require_relative 'token_node'
 require_relative 'non_terminal_node'
+require_relative 'alternative_node'
 
 module Rley # This module is used as a namespace
   module SPPF # This module is used as a namespace
@@ -18,17 +19,28 @@ module Rley # This module is used as a namespace
       
       # A Hash with pairs of the kind node key => node
       attr_reader(:key2node)
+      
+      # A setter that tells that the parse is ambiguous.
+      attr_writer(:is_ambiguous)
+
 
       # @param theRootNode [ParseForestNode] The root node of the parse tree.
       def initialize(theRootNode)
         @root = theRootNode
         @key2node = {}
+        @is_ambiguous = false
       end
       
       # Returns true if the given node is present in the forest.
       def include?(aNode)
         return key2node.include?(aNode)
       end
+      
+      # Returns true if the parse encountered a structural ambiguity
+      # (i.e. more than one parse tree for the given input)
+      def ambiguous?()
+        return @is_ambiguous
+      end
 
 
       # Part of the 'visitee' role in the Visitor design pattern.

data/lib/rley/syntax/grammar_builder.rb

@@ -18,9 +18,12 @@ module Rley # This module is used as a namespace
       # The list of production rules for the grammar to build
       attr_reader(:productions)
 
-      def initialize()
+
+      def initialize(&aBlock)
         @symbols = {}
         @productions = []
+
+        instance_exec(&aBlock) if block_given?
       end
       
       # Retrieve a grammar symbol from its name.
@@ -87,6 +90,8 @@ module Rley # This module is used as a namespace
         
         return @grammar
       end
+      
+      alias rule add_production
 
       private
 

data/spec/rley/parser/parse_forest_factory_spec.rb

@@ -17,7 +17,7 @@ module Rley # Open this namespace to avoid module qualifier prefixes
 
       let(:sample_grammar) do
           # Grammar based on paper from Elisabeth Scott
-          # "SPPF=Style Parsing From Earley Recognizers" in
+          # "SPPF-Style Parsing From Earley Recognizers" in
           # Notes in Theoretical Computer Science 203, (2008), pp. 53-67
           # contains a hidden left recursion and a cycle
           builder = Syntax::GrammarBuilder.new

data/spec/rley/syntax/grammar_builder_spec.rb

@@ -6,10 +6,10 @@ require_relative '../../../lib/rley/syntax/grammar_builder'
 module Rley # Open this namespace to avoid module qualifier prefixes
   module Syntax # Open this namespace to avoid module qualifier prefixes
     describe GrammarBuilder do
-      context 'Initialization:' do
-        it 'should be created without argument' do
+      context 'Initialization without argument:' do
+        it 'could be created without argument' do
           expect { GrammarBuilder.new }.not_to raise_error
-        end
+        end   
 
         it 'should have no grammar symbols at start' do
             expect(subject.symbols).to be_empty
@@ -19,6 +19,24 @@ module Rley # Open this namespace to avoid module qualifier prefixes
             expect(subject.productions).to be_empty
         end
       end # context
+      
+      context 'Initialization with argument:' do
+        it 'could be created with a block argument' do
+          expect do GrammarBuilder.new { nil }
+          end.not_to raise_error
+        end        
+
+        it 'could have grammar symbols from block argument' do
+          instance = GrammarBuilder.new do
+            add_terminals('a', 'b', 'c')
+          end
+          expect(instance.symbols.size).to eq(3)
+        end
+
+        it 'should have no productions at start' do
+            expect(subject.productions).to be_empty
+        end
+      end # context      
 
       context 'Adding symbols:' do
         it 'should build terminals from their names' do
@@ -79,7 +97,8 @@ module Rley # Open this namespace to avoid module qualifier prefixes
           expect_rhs = [ subject['a'], subject['A'], subject['c'] ]
           expect(new_prod.rhs.members).to eq(expect_rhs)
 
-          subject.add_production('A' => ['b'])
+          # GrammarBuilder#rule is an alias of add_production
+          subject.rule('A' => ['b'])
           expect(subject.productions.size).to eq(3)
           new_prod = subject.productions.last
           expect(new_prod.lhs).to eq(subject['A'])
@@ -89,11 +108,13 @@ module Rley # Open this namespace to avoid module qualifier prefixes
 
       context 'Building grammar:' do
         subject do
-          instance = GrammarBuilder.new
-          instance.add_terminals('a', 'b', 'c')
-          instance.add_production('S' => ['A'])
-          instance.add_production('A' => %w(a A c))
-          instance.add_production('A' => ['b'])
+          instance = GrammarBuilder.new do
+            add_terminals('a', 'b', 'c')
+            add_production('S' => ['A'])
+            add_production('A' => %w(a A c))
+            add_production('A' => ['b'])
+          end
+
           instance
         end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rley
 version: !ruby/object:Gem::Version
-  version: 0.3.09
+  version: 0.3.10
 platform: ruby
 authors:
 - Dimitri Geshef
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-11-27 00:00:00.000000000 Z
+date: 2016-12-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake