rley 0.7.00 → 0.7.01

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 2b462d4c492ffb698715478492a962d65e41834c
-  data.tar.gz: 282ab2ed83d7b1ead2646c8dd98176d1753a142e
+  metadata.gz: 1d453e82683bb3a51986dad86b0b34d100fd4c27
+  data.tar.gz: bce3fa7704cb65670102ecfcb78ee762bdad7ba5
 SHA512:
-  metadata.gz: 514e4a9429b4fd1231001269cd18e96fa70d4b9145c60115f042f338e0a0063871f979ba9c04e971ee589c8e2d3919fece6b3af4499af50f03899f44318a0598
-  data.tar.gz: 870e01cb9e693c126b9fa13915dadcec72559553147e0bf220f6e39a6431c6b59c7fb1b67aa1a19d8eadf0076fc6378948fbf1f56850c88d9f99584fefb7f259
+  metadata.gz: bfba908cc187a280ed9a236414cd79ff9880abc96997acdb8c33a4c36f39731ca9b2d4c99be6e2adfb45ef053bd275ba052d8a2d61e851f6607b9ebd2248d1c8
+  data.tar.gz: 1b20d6ebe85f9d174a7ce8e2a5729e7eaa09fffa0550eb6e586592dd24d4b3cc0c309139b1d2368178309a2ed1eb411c3e07e05509152491961248c8a61492ea

data/.rubocop.yml

@@ -1,20 +1,20 @@
 AllCops:
   Exclude:
     - 'features/**/*'
-    - 'exp/**/*'    
+    - 'exp/**/*'
     - 'gems/**/*'
     - 'refs/**/*'
-    
+
 # This is disabled because some demos use UTF-8
 AsciiComments:
   Enabled: false
-  
+
 Attr:
   Enabled: false
-  
+
 BlockComments:
   Enabled: false
-  
+
 CaseIndentation:
   EnforcedStyle: end
   IndentOneStep: true
@@ -23,89 +23,106 @@ CaseIndentation:
 # Which is contrary to modelling practice.
 ClassCheck:
   Enabled: false
-  
+
 ClassLength:
   Max: 250
-  CountComments: false  
+  CountComments: false
 
-ConstantName:  
+ConstantName:
   Enabled: false
-  
+
 CyclomaticComplexity:
   Enabled: false
-  
-DefWithParentheses:  
+
+DefWithParentheses:
   Enabled: false
-  
+
 Documentation:
   Enabled: false
-  
+
 EmptyLines:
-  Enabled: false 
+  Enabled: false
 
 Encoding:
   Enabled: false
-  
+
 EndOfLine:
   Enabled: false
 #  SupportedStyles: lf
-  
-  
-IndentationWidth :
+
+
+IndentationWidth:
   Enabled: false
   
-# Disable this because it produces false negatives
-Naming/HeredocDelimiterNaming:
+Layout/BlockAlignment:
+  Enabled: false
+
+Layout/ClosingHeredocIndentation:
   Enabled: false
   
 # Enabled after end of support of Rubies < 2.3
 Layout/IndentHeredoc:
   Enabled: false
 
+Layout/SpaceInsideArrayLiteralBrackets:
+  Enabled: false  
+  
 Metrics/AbcSize:
   Max: 50
-  
+
 # Avoid methods longer than 50 lines of code
 Metrics/MethodLength:
   Max: 50
-  CountComments: false 
+  CountComments: false
 
-# Avoid modules longer than 200 lines of code 
+# Avoid modules longer than 200 lines of code
 Metrics/ModuleLength:
   CountComments: false
-  Max: 200  
+  Max: 200
 
 Metrics/PerceivedComplexity:
   Enabled: true
   Max: 50
   
+# Disable this because it produces false negatives
+Naming/HeredocDelimiterNaming:
+  Enabled: false
+
 Naming/MethodName:
   Enabled: false
- 
+
+Naming/UncommunicativeMethodParamName:
+  Enabled: false
+
 NonNilCheck:
   Enabled: false
 
 NumericLiterals:
   Enabled: false
-  
+
 RaiseArgs:
   Enabled: false
-  
+
 RedundantReturn:
   Enabled: false
 
-SpaceInsideBrackets:
+Style/CommentedKeyword:
+  Enabled: false
+  
+Style/ConditionalAssignment:  
+  Enabled: false
+  
+Style/Lambda:
+  Enabled: false
+  
+Style/MissingRespondToMissing:
   Enabled: false
 
 TrailingWhitespace:
   Enabled: false
-  
+
 VariableName:
   Enabled: false
 
 VariableNumber:
-  Enabled: false
-  
-Style/CommentedKeyword:
-  Enabled: false
-  
+  Enabled: false

data/.travis.yml

@@ -1,14 +1,15 @@
 language: ruby
 rvm:
-  - 2.0.0-p648
+  - 2.6.0
+  - 2.5.3
+  - 2.4.5
+  - 2.3.8
+  - 2.2.10
   - 2.1.10
-  - 2.2.8
-  - 2.3.6
-  - 2.4.2
-  - 2.5.0
+  - 2.0.0-p648
   - ruby-head
-  - jruby-9.1.13.0    
-  - jruby-head 
+  - jruby-9.1.9.0
+  - jruby-head
 matrix:
   allow_failures:
     - rvm: ruby-head
@@ -16,8 +17,8 @@ matrix:
 
 gemfile:
   - Gemfile
-  
+
 # whitelist
-branches:  
+branches:
   only:
     - master

data/CHANGELOG.md

@@ -1,3 +1,12 @@
+### 0.7.01 / 2019-01-03  
+- Maintenance release.
+
+* [CHANGE] Code re-styling to please Rubocop 0.62.0.
+* [CHANGE] File `.travis.yml`: updated Ruby versions.
+* [CHANGE] File `appveyor.yml` updated Ruby versions.
+* [CHANGE] File `README.me` removal obsolete icon.
+* [CHANGE] File `LICENSE.txt` Updated copyright years.
+
 ### 0.7.00 / 2018-11-24  
 - Version bump. Core class `Token` is changed.
 

data/LICENSE.txt

@@ -1,4 +1,4 @@
-Copyright (c) 2014-2018 Dimitri Geshef
+Copyright (c) 2014-2019 Dimitri Geshef
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

data/README.md

@@ -4,7 +4,6 @@
 [![Build status](https://ci.appveyor.com/api/projects/status/l5adgcbfo128rvo9?svg=true)](https://ci.appveyor.com/project/famished-tiger/rley)
 [![Coverage Status](https://img.shields.io/coveralls/famished-tiger/Rley.svg)](https://coveralls.io/r/famished-tiger/Rley?branch=master)
 [![Gem Version](https://badge.fury.io/rb/rley.svg)](http://badge.fury.io/rb/rley)
-[![Dependency Status](https://gemnasium.com/famished-tiger/Rley.svg)](https://gemnasium.com/famished-tiger/Rley)
 [![Inline docs](http://inch-ci.org/github/famished-tiger/Rley.svg?branch=master)](http://inch-ci.org/github/famished-tiger/Rley)
 [![License](https://img.shields.io/badge/license-MIT-brightgreen.svg?style=flat)](https://github.com/famished-tiger/SRL-Ruby/blob/master/LICENSE.txt)
 

data/appveyor.yml

@@ -2,16 +2,18 @@ version: '{build}'
 max_jobs: 3
 environment:
   matrix:
-  - Ruby_version: 200
-  - Ruby_version: 200-x64
-  - Ruby_version: 21
-  - Ruby_version: 21-x64
-  - Ruby_version: 22
-  - Ruby_version: 22-x64
-  - Ruby_version: 23
+  #- Ruby_version: 25-x64   
+  - Ruby_version: 24-x64  
   - Ruby_version: 23-x64
+  - Ruby_version: 22-x64
+  - Ruby_version: 21-x64
+  - Ruby_version: 200-x64
+  #- Ruby_version: 25   
   - Ruby_version: 24  
-  - Ruby_version: 24-x64 
+  - Ruby_version: 23
+  - Ruby_version: 22
+  - Ruby_version: 21
+  - Ruby_version: 200  
 
 install:
   - set PATH=C:\Ruby%Ruby_version%\bin;%PATH%

data/examples/NLP/benchmark_pico_en.rb

@@ -5,7 +5,7 @@ require 'rley' # Load Rley library
 
 ########################################
 # Step 0. Instantiate facade object of Rley library.
-# It provides a unified, higher-level interface 
+# It provides a unified, higher-level interface
 engine = Rley::Engine.new
 
 ########################################
@@ -67,8 +67,9 @@ def tokenizer(aTextToParse)
   tokens = aTextToParse.scan(/\S+/).map do |word|
     term_name = Lexicon[word]
     raise StandardError, "Word '#{word}' not found in lexicon" if term_name.nil?
+
     pos = Rley::Lexical::Position.new(1, offset + 1)
-    offset += word.length 
+    offset += word.length
     Rley::Lexical::Token.new(word, term_name, pos)
   end
 

data/examples/NLP/engtagger.rb

@@ -2,12 +2,13 @@ require 'rley'
 require 'engtagger' # Load POS (Part-Of-Speech) tagger EngTagger
 
 # REGEX to remove XML tags from Engtagger output
-GET_TAG = /<(.+?)>(.*?)<.+?>/
+GET_TAG = /<(.+?)>(.*?)<.+?>/.freeze
 
 # Text tokenizer
 # Taken directly from Engtagger, will ensure uniform indexing while parsing
 def clean_text(text)
     return false unless valid_text(text)
+
     text = text.toutf8
     cleaned_text = text
     tokenized = []
@@ -48,13 +49,14 @@ def split_sentences(array)
                 va wash wis wisc wy wyo usafa alta man ont que sask yuk]
     month  = %w[jan feb mar apr may jun jul aug sep sept oct nov dec]
     misc   = %w[vs etc no esp]
-    abbr = Hash.new
+    abbr = {}
     [people, army, inst, place, comp, state, month, misc].flatten.each do |i|
       abbr[i] = true
     end
-    words = Array.new
+    words = []
     tokenized.each_with_index do |_t, i|
-      if tokenized[i + 1] && tokenized [i + 1] =~ /[A-Z\W]/ && tokenized[i] =~ /\A(.+)\.\z/
+      if tokenized[i + 1] &&
+         tokenized [i + 1] =~ /[A-Z\W]/ && tokenized[i] =~ /\A(.+)\.\z/
         w = $1
         # Don't separate the period off words that
         # meet any of the following conditions:
@@ -62,8 +64,9 @@ def split_sentences(array)
         # 1. It is defined in one of the lists above
         # 2. It is only one letter long: Alfred E. Sloan
         # 3. It has a repeating letter-dot: U.S.A. or J.C. Penney
-        unless abbr[w.downcase] || w =~ /\A[a-z]\z/i || w =~ /[a-z](?:\.[a-z])+\z/i
-          words <<  w
+        unless abbr[w.downcase] ||
+               w =~ /\A[a-z]\z/i || w =~ /[a-z](?:\.[a-z])+\z/i
+          words << w
           words << '.'
           next
         end
@@ -83,15 +86,20 @@ end
 def split_punct(text)
     # If there's no punctuation, return immediately
     return [text] if /\A\w+\z/ =~ text
+
     # Sanity checks
     text = text.gsub(/\W{10,}/o, ' ')
 
     # Put quotes into a standard format
     text = text.gsub(/`(?!`)(?=.*\w)/o, '` ') # Shift left quotes off text
     text = text.gsub(/"(?=.*\w)/o, ' `` ') # Convert left quotes to ``
-    text = text.gsub(/(\W|^)'(?=.*\w)/o) { $1 ? $1 + ' ` ' : ' ` ' } # Convert left quote to `
+
+    # Convert left quote to `
+    text = text.gsub(/(\W|^)'(?=.*\w)/o) { $1 ? $1 + ' ` ' : ' ` ' }
     text = text.gsub(/"/, " '' ") # Convert (remaining) quotes to ''
-    text = text.gsub(/(\w)'(?!')(?=\W|$)/o, "\\1 ' ") # Separate right single quotes
+
+    # Separate right single quotes
+    text = text.gsub(/(\w)'(?!')(?=\W|$)/o, "\\1 ' ")
 
     # Handle all other punctuation
     text = text.gsub(/--+/o, ' - ') # Convert and separate dashes
@@ -99,10 +107,13 @@ def split_punct(text)
     text = text.gsub(/:/o, ' :') # Shift semicolon off
     text = text.gsub(/(\.\.\.+)/o, ' \1 ') # Shift ellipses off
     text = text.gsub(/([\(\[\{\}\]\)])/o, ' \1 ') # Shift off brackets
-    text = text.gsub(/([\!\?#\$%;~|])/o, ' \1 ') # Shift off other ``standard'' punctuation
+
+    # Shift off other ``standard'' punctuation
+    text = text.gsub(/([\!\?#\$%;~|])/o, ' \1 ')
 
     # English-specific contractions
-    text = text.gsub(/([A-Za-z])'([dms])\b/o, "\\1 '\\2") # Separate off 'd 'm 's
+    # Separate off 'd 'm 's
+    text = text.gsub(/([A-Za-z])'([dms])\b/o, "\\1 '\\2")
     text = text.gsub(/n't\b/o, " n't") # Separate off n't
     text = text.gsub(/'(ve|ll|re)\b/o, " '\\1") # Separate off 've, 'll, 're
     result = text.split(' ')
@@ -139,7 +150,7 @@ tgr = EngTagger.new
 tagged = tgr.add_tags(text)
 
 # Generte tokenied lexicon of input text
-# Instead of creating a lexicon dictionary, 
+# Instead of creating a lexicon dictionary,
 # we would simply generate one each time on the fly for the current text only.
 lexicon = clean_text(text)
 
@@ -153,7 +164,7 @@ def tokenizer(lexicon, tokens)
     term_name = tokens[i].last
     rank = Rley::Lexical::Position.new(1, pos + 1)
     pos += word.length + 1 # Assuming one space between words.
-    rley_tokens << Rley::Lexical::Token.new(word, term_name, pos)
+    rley_tokens << Rley::Lexical::Token.new(word, term_name, rank)
   end
   return rley_tokens
 end

data/examples/NLP/nano_eng/nano_en_demo.rb

@@ -68,10 +68,10 @@ Lexicon = {
 # Step 4. Creating a tokenizer
 # A tokenizer reads the input string and converts it into a sequence of tokens
 # Highly simplified tokenizer implementation.
-def tokenizer(aTextToParse) 
+def tokenizer(aTextToParse)
   scanner = StringScanner.new(aTextToParse)
   tokens = []
-  
+
   loop do
     scanner.skip(/\s+/)
     curr_pos = scanner.pos
@@ -80,11 +80,12 @@ def tokenizer(aTextToParse)
 
     term_name = Lexicon[word]
     raise StandardError, "Word '#{word}' not found in lexicon" if term_name.nil?
+
     pos = Rley::Lexical::Position.new(1, curr_pos + 1)
     tokens << Rley::Lexical::Token.new(word, term_name, pos)
   end
 
-  return tokens  
+  return tokens
 end
 
 

data/examples/NLP/pico_en_demo.rb

@@ -64,7 +64,7 @@ Lexicon = {
 def tokenizer(aTextToParse)
   scanner = StringScanner.new(aTextToParse)
   tokens = []
-  
+
   loop do
     scanner.skip(/\s+/)
     curr_pos = scanner.pos
@@ -73,6 +73,7 @@ def tokenizer(aTextToParse)
 
     term_name = Lexicon[word]
     raise StandardError, "Word '#{word}' not found in lexicon" if term_name.nil?
+
     pos = Rley::Lexical::Position.new(1, curr_pos + 1)
     tokens << Rley::Lexical::Token.new(word, term_name, pos)
   end
@@ -94,7 +95,7 @@ unless result.success?
   puts result.failure_reason.message
   exit(1)
 end
- 
+
 ########################################
 # Step 6. Generating a parse tree from parse result
 ptree = engine.to_ptree(result)

data/examples/data_formats/JSON/json_ast_nodes.rb

@@ -29,6 +29,7 @@ JSONTerminalNode = Struct.new(:token, :value, :position) do
   end
   
   def done!
+    # Do nothing  
   end
 end
 
@@ -76,6 +77,7 @@ class JSONCompositeNode
   end
   
   def done!
+    # Do nothing  
   end
 
   alias subnodes children
@@ -123,6 +125,7 @@ class JSONPair
   end
   
   def done!
+    # Do nothing
   end
   
   def to_ruby