rley 0.5.06 → 0.5.07

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 330046979feed860a18faeb226de2c2aab9ca8ca
-  data.tar.gz: 3e8b7ee124edb3db95f6c95c56754a71375dd703
+  metadata.gz: 4ce368c99ffa556898d9a89788786e47b5e8b115
+  data.tar.gz: 97a691b869089989f601556ed13dd24d729b7ad0
 SHA512:
-  metadata.gz: 518f9fb02230a1953c71ac4334cfa71d4c72c3f9e94b546a7dd164a32aa67d0ab2769563cd5cd72b46891cbce08fe9d4319f6645de7db8bd2ddb5d8fab67034a
-  data.tar.gz: b468cda9c0d4c0e49537f0fc4cdac5882ea21ee176810c0d529fda1f080e13428f73a328607afff640f51ded1de8c83e4a5715da008d4295a276064d78490ca5
+  metadata.gz: b50595273bf5f75e25b6e609de197be31a4f8583f1c1f93ef8494a8e5367facdbafd13326bd2097c9da657096c2f15e9dc8d439d16212f4e578134ce538984b2
+  data.tar.gz: 8be6b6bdef48de1cbd19b2785530a5bc17e43804a43ff01f287a89a129a83897f8ea05ecb951018c99f888bbfefbbc33e89ee9cfb0adb2e86eba2e3971703c1d

data/.travis.yml

@@ -2,9 +2,9 @@ language: ruby
 rvm:
   - 2.0.0-p648
   - 2.1.10
-  - 2.2.7
-  - 2.3.4
-  - 2.4.1
+  - 2.2.8
+  - 2.3.5
+  - 2.4.2
   - ruby-head
   - jruby-9.1.9.0    
   - jruby-head 

data/CHANGELOG.md

@@ -1,3 +1,8 @@
+### 0.5.07 / 2017-11-11
+* [NEW] File `benchmark_mini_en.rb` added in `examples/NLP` folder for parsing performance measurements.
+* [CHANGE] Demo calculator in `examples/general/calc_iter2`: added support for log10 and cbrt functions. README.md slightly reworked.
+* [FIX] File `README.md` sample code was broken by changes in 0.5.06 (thanks to arjunmenon for pointing this).
+
 ### 0.5.06 / 2017-11-08
 * [CHANGE] Demo calculator in `examples/general/calc_iter2` does much than the basic arithmetic operators, it now  
 support trigonometric functions and their inverse, square root, exponential and natural logarithm functions!.

data/README.md

@@ -148,7 +148,7 @@ The subset of English grammar is based on an example from the NLTK book.
         term_name = Lexicon[word]
         raise StandardError, "Word '#{word}' not found in lexicon" if term_name.nil?
         terminal = aGrammar.name2symbol[term_name]
-        Rley::Tokens::Token.new(word, terminal)
+        Rley::Lexical::Token.new(word, terminal)
       end
 
       return tokens

data/examples/NLP/benchmark_mini_en.rb

@@ -0,0 +1,92 @@
+# File: benchmark_mini_en.rb
+# Purpose: benchmark the parse speed
+require 'benchmark'
+require 'rley' # Load Rley library
+
+# Instantiate a builder object that will build the grammar for us
+builder = Rley::Syntax::GrammarBuilder.new do
+
+  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
+
+########################################
+# Step 2. Creating a lexicon
+# To simplify things, lexicon is implemented as a Hash with pairs of the form:
+# word => terminal symbol name
+Lexicon = {
+  'man' => 'Noun',
+  'dog' => 'Noun',
+  'cat' => 'Noun',
+  'telescope' => 'Noun',
+  'park' => 'Noun',  
+  'saw' => 'Verb',
+  'ate' => 'Verb',
+  'walked' => 'Verb',
+  'John' => 'Proper-Noun',
+  'Mary' => 'Proper-Noun',
+  'Bob' => 'Proper-Noun',
+  'a' => 'Determiner',
+  'an' => 'Determiner',
+  'the' => 'Determiner',
+  'my' => 'Determiner',
+  'in' => 'Preposition',
+  'on' => 'Preposition',
+  'by' => 'Preposition',
+  'with' => 'Preposition'
+}.freeze
+
+########################################
+# Step 3. Creating a tokenizer
+# A tokenizer reads the input string and converts it into a sequence of tokens
+# Highly simplified tokenizer implementation.
+def tokenizer(aTextToParse, aGrammar)
+  tokens = aTextToParse.scan(/\S+/).map do |word|
+    term_name = Lexicon[word]
+    raise StandardError, "Word '#{word}' not found in lexicon" if term_name.nil?
+    terminal = aGrammar.name2symbol[term_name]
+    Rley::Lexical::Token.new(word, terminal)
+  end
+  
+  return tokens
+end
+
+########################################
+# Step 4. Create a parser for that grammar
+# Easy with Rley...
+parser = Rley::Parser::GFGEarleyParser.new(grammar)
+
+########################################
+# Step 5. Parsing the input
+input_to_parse = 'John saw Mary with a telescope'
+
+# Convert input text into a sequence of token objects...
+tokens = tokenizer(input_to_parse, grammar)
+
+# Use Benchmark mix-in
+include Benchmark
+
+bm(6) do |meter|
+  meter.report("Parse 100 times") { 100.times { parser.parse(tokens) } }
+  meter.report("Parse 1000 times") { 1000.times { parser.parse(tokens) } }
+  meter.report("Parse 10000 times") { 10000.times { parser.parse(tokens) } }
+  meter.report("Parse 1000000 times") { 100000.times { parser.parse(tokens) } }
+end
+
+# puts "Parsing successful? #{result.success?}"
+# unless result.success?
+  # puts result.failure_reason.message
+  # exit(1)
+# end

data/examples/general/calc_iter2/calc_ast_nodes.rb

@@ -97,11 +97,18 @@ class CalcNegateNode < CalcUnaryOpNode
 end # class
 
 class CalcUnaryFunction < CalcCompositeNode
+  @@name_mapping = begin 
+    map = Hash.new { |me, key| me[key] = key }
+    map['ln'] = 'log'
+    map['log'] = 'log10'
+    map
+  end
   attr_accessor(:func_name)
   
+  
   def interpret()
     argument = children[0].interpret
-    internal_name = @func_name == 'ln' ? 'log' : @func_name
+    internal_name = @@name_mapping[@func_name] # @func_name == 'ln' ? 'log' : @func_name
     return Math.send(internal_name.to_sym, argument)
   end  
 end

data/examples/general/calc_iter2/calc_lexer.rb

@@ -24,7 +24,8 @@ class CalcLexer
   @@unary_functions = [
     'sin', 'cos', 'tan',
     'asin', 'acos', 'atan',
-    'sqrt', 'exp', 'ln'
+    'sqrt', 'cbrt', 'exp', 
+    'ln', 'log'
   ].freeze
 
   class ScanError < StandardError; end

data/examples/general/calc_iter2/spec/calculator_spec.rb

@@ -168,8 +168,18 @@ describe 'Calculator' do
     
     # Some special functions
     it 'should evaluate square root of expressions' do
+      expect_expr('sqrt(0)').to eq(0)
+      expect_expr('sqrt(1)').to eq(1)
       expect_expr('sqrt(1 + 1)').to eq(Math.sqrt(2))
-    end 
+      expect_expr('sqrt(5 * 5)').to eq(5)
+    end
+
+    it 'should evaluate cubic root of expressions' do
+      expect_expr('cbrt(0)').to eq(0)
+      expect_expr('cbrt(1)').to eq(1)
+      expect_expr('cbrt(1 + 1)').to eq(Math.cbrt(2))
+      expect_expr('cbrt(5 * 5 * 5)').to eq(5)
+    end     
 
     it 'should evaluate exponential of expressions' do
       expect_expr('exp(-1)').to eq(1/Math::E)    
@@ -183,7 +193,14 @@ describe 'Calculator' do
       expect_expr('ln(1)').to eq(0)    
       expect_expr('ln(E)').to eq(1)
       expect_expr('ln(E * E)').to eq(2)
-    end     
+    end 
+
+    it 'should evaluate the logarithm base 10 of expressions' do
+      expect_expr('log(1/10)').to eq(-1)    
+      expect_expr('log(1)').to eq(0)    
+      expect_expr('log(10)').to eq(1)
+      expect_expr('log(10 * 10 * 10)').to eq(3)
+    end    
  
     # Trigonometric functions
     

data/lib/rley/constants.rb

@@ -3,7 +3,7 @@
 
 module Rley # Module used as a namespace
   # The version number of the gem.
-  Version = '0.5.06'.freeze
+  Version = '0.5.07'.freeze
 
   # Brief description of the gem.
   Description = "Ruby implementation of the Earley's parsing algorithm".freeze

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rley
 version: !ruby/object:Gem::Version
-  version: 0.5.06
+  version: 0.5.07
 platform: ruby
 authors:
 - Dimitri Geshef
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-11-08 00:00:00.000000000 Z
+date: 2017-11-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: coveralls
@@ -130,6 +130,7 @@ files:
 - README.md
 - Rakefile
 - appveyor.yml
+- examples/NLP/benchmark_mini_en.rb
 - examples/NLP/mini_en_demo.rb
 - examples/data_formats/JSON/cli_options.rb
 - examples/data_formats/JSON/json_ast_builder.rb