opener-opinion-detector-basic 3.2.2 → 3.2.6

data/lib/opener/opinion_detector_basic/version.rb

@@ -1,7 +1,7 @@
 module Opener
   class OpinionDetectorBasic
 
-    VERSION = '3.2.2'
+    VERSION = '3.2.6'
 
   end
 end

data/opener-opinion-detector-basic.gemspec

@@ -27,7 +27,9 @@ Gem::Specification.new do |gem|
   gem.add_dependency 'opener-webservice', '~> 2.1'
   gem.add_dependency 'opener-core', '~> 2.2'
 
-  gem.add_dependency 'oga', ['~> 1.0', '>= 1.3.1']
+  gem.add_dependency 'activesupport'
+  gem.add_dependency 'nokogiri'
+  gem.add_dependency 'hashie'
 
   gem.add_development_dependency 'rspec', '~> 3.0'
   gem.add_development_dependency 'cucumber'

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: opener-opinion-detector-basic
 version: !ruby/object:Gem::Version
-  version: 3.2.2
+  version: 3.2.6
 platform: ruby
 authors:
 - development@olery.com
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-11-04 00:00:00.000000000 Z
+date: 2021-08-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: opener-daemons
@@ -53,25 +53,47 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '2.2'
 - !ruby/object:Gem::Dependency
-  name: oga
+  name: activesupport
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.0'
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.3.1
+        version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: hashie
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.0'
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.3.1
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
@@ -145,12 +167,15 @@ files:
 - config.ru
 - exec/opinion-detector-basic.rb
 - lib/opener/opinion_detector_basic.rb
+- lib/opener/opinion_detector_basic/base_processor.rb
 - lib/opener/opinion_detector_basic/cli.rb
-- lib/opener/opinion_detector_basic/opinion.rb
+- lib/opener/opinion_detector_basic/kaf/document.rb
+- lib/opener/opinion_detector_basic/kaf/opinion.rb
+- lib/opener/opinion_detector_basic/kaf/term.rb
+- lib/opener/opinion_detector_basic/legacy_processor.rb
 - lib/opener/opinion_detector_basic/processor.rb
 - lib/opener/opinion_detector_basic/public/markdown.css
 - lib/opener/opinion_detector_basic/server.rb
-- lib/opener/opinion_detector_basic/term.rb
 - lib/opener/opinion_detector_basic/version.rb
 - lib/opener/opinion_detector_basic/views/index.erb
 - opener-opinion-detector-basic.gemspec
@@ -174,8 +199,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project:
-rubygems_version: 2.7.6
+rubygems_version: 3.2.14
 signing_key:
 specification_version: 4
 summary: Basic Opinion Detector.

data/lib/opener/opinion_detector_basic/opinion.rb

@@ -1,170 +0,0 @@
-module Opener
-  class OpinionDetectorBasic
-    class Opinion
-      attr_reader :term
-      attr_accessor :left_candidates, :right_candidates, :target_ids, :holders
-
-      # Opinion holders for each language code.
-      OPINION_HOLDERS = {
-        'nl' => [
-          'ik','we','wij','ze','zij','jullie','u','hij','het','jij','je','mij',
-          'me','hem','haar','ons','hen','hun'
-        ],
-        'en' => ['i','we','he','she','they','it','you'],
-        'es' => [
-          'yo','tu','nosotros','vosotros','ellos','ellas','nosotras','vosotras'
-        ],
-        'it' => ['io','tu','noi','voi','loro','lei','lui'],
-        'de' => ['ich','du','wir','ihr','sie','er'],
-        'fr' => ['je','tu','lui','elle','nous','vous','ils','elles']
-      }
-
-      def initialize(term)
-        @term = term
-        @left_candidates = []
-        @right_candidates = []
-        @holders = []
-        @target_ids = []
-      end
-
-      ##
-      # Returns the term ids of the opinion expression.
-      #
-      # @return [Array]
-      #
-      def ids
-        @ids ||= term.list_ids.sort
-      end
-
-      ##
-      # Returns the sentence id of the opinion.
-      #
-      # @return [String]
-      #
-      def sentence
-        @sentence ||= term.sentence
-      end
-
-      ##
-      # Returns the strength of the opinion.
-      #
-      # @return [Integer]
-      #
-      def strength
-        @strength ||= term.accumulated_strength
-      end
-
-      ##
-      # Returns the polarity of the opinion.
-      #
-      # @return [String]
-      #
-      def polarity
-        @polarity ||= if strength > 0
-          "positive"
-        elsif strength < 0
-          "negative"
-        else
-          "neutral"
-        end
-      end
-
-      ##
-      # Obtain the opinion holders from the terms that belong to the same
-      # sentence.
-      #
-      def obtain_holders(sentences, language)
-        sentence_terms = sentences[sentence]
-        sentence_terms.each do |term|
-          if OPINION_HOLDERS[language]&.include?(term.lemma)
-            @holders << term.id
-            break
-          end
-        end
-      end
-
-      ##
-      # Get the potential right and left candidates of the sentence and
-      # decide which ones are the actual targets of the opinion
-      #
-      def obtain_targets(sentences)
-        sentence_terms = sentences[sentence]
-        max_distance = 3
-        terms_count = sentence_terms.count
-
-        index = -1
-        sentence_terms.each_with_index do |term, i|
-          if ids.include?(term.id)
-            index = i
-          end
-        end
-
-        unless index+1 >= terms_count
-          min = index+1
-          max = [index+1+max_distance,terms_count].min
-          @right_candidates = filter_candidates(sentence_terms[min..max])
-        end
-
-        index = 0
-        sentence_terms.each_with_index do |term, i|
-          if ids.include?(term.id)
-            index = i
-            break # needed for left_candidates
-          end
-        end
-
-        unless index == 0
-          min = [0, index-1-max_distance].max
-          max = index
-          @left_candidates = filter_candidates(sentence_terms[min..max])
-        end
-
-        unless right_candidates.empty?
-          candidate = right_candidates.first
-          @target_ids << candidate.id
-        end
-
-        if target_ids.empty?
-          list = mix_lists(right_candidates, left_candidates)
-          list.each do |l|
-            @target_ids << l.id
-            break
-          end
-        end
-      end
-
-      protected
-
-      ##
-      # If there are no opinion targets, right and left candidates
-      # are mixed into one list and the first one is picked as the target.
-      #
-      # @return [Array]
-      #
-      def mix_lists(lista, listb)
-        list = []
-        min = [lista.count, listb.count].min
-        (0..min).each do |i|
-          list << lista[i]
-          list << listb[i]
-          if lista.count > listb.count
-            list << lista[min]
-          elsif listb.count > lista.count
-            list << listb[min]
-          end
-        end
-        return list.compact
-      end
-
-      ##
-      # Filters candidate terms depending on their part of speech and if
-      # they are already part of the expression.
-      #
-      # @return [Hash]
-      #
-      def filter_candidates(sentence_terms)
-        sentence_terms.select{|t| (t.pos == "N" || t.pos == "R") && !ids.include?(t.id)}
-      end
-    end # Opinion
-  end # OpinionDetectorBasic
-end # Opener

data/lib/opener/opinion_detector_basic/term.rb

@@ -1,159 +0,0 @@
-module Opener
-  class OpinionDetectorBasic
-    class Term
-      attr_reader :node, :sentence, :is_conjunction
-      attr_accessor :use, :accumulated_strength, :list_ids
-
-      # Map of conjunctions per language code
-      CONJUNCTIONS = {
-        'nl' => %w{, en},
-        'en' => %w{, and},
-        'es' => %w{, y e},
-        'it' => %w{, e ed},
-        'de' => %w{, und},
-        'fr' => %w{, et}
-      }
-
-      def initialize(node, document, language)
-        @node                 = node
-        @sentence             = get_sentence(document)
-        @use                  = true
-        @accumulated_strength = strength
-        @list_ids             = [id]
-        @is_conjunction       = is_conjunction?(language)
-      end
-
-      ##
-      # Returns the term id.
-      #
-      # @return [String]
-      #
-      def id
-        @id ||= node.get('tid')
-      end
-
-      ##
-      # Returns the lemma of the term.
-      #
-      # @return [String]
-      #
-      def lemma
-        @lemma ||= node.get('lemma')
-      end
-
-      ##
-      # Returns the part of speech of the term.
-      #
-      # @return [String]
-      #
-      def pos
-        @pos ||= node.get('pos')
-      end
-
-      ##
-      # Returns the sentiment modifier type if it exists.
-      #
-      # @return [String|NilClass]
-      #
-      def sentiment_modifier
-        @sentiment_modifier ||=
-          first_sentiment ? first_sentiment.get('sentiment_modifier') : nil
-      end
-
-      ##
-      # Returns the polarity of the term if it exists.
-      #
-      # @return [String|NilClass]
-      #
-      def polarity
-        @polarity ||= first_sentiment ? first_sentiment.get('polarity') : nil
-      end
-
-      ##
-      # Returns the actual word ids that construct the lemma.
-      #
-      # @return [Array]
-      #
-      def target_ids
-        @target_ids ||= node.xpath('span/target')
-          .map { |target| target.get('id') }
-      end
-
-      ##
-      # Returns the strength of the term depending on its type.
-      #
-      # @return [Integer]
-      #
-      def strength
-        if polarity == "positive"
-          return 1
-        elsif polarity == "negative"
-          return -1
-        end
-
-        if is_intensifier?
-          return 2
-        elsif is_shifter?
-          return -1
-        end
-
-        return 0
-      end
-
-      ##
-      # Returns the sentence id that the term belongs to in the document.
-      #
-      # @return [String]
-      #
-      def get_sentence(document)
-        document
-        .xpath("KAF/text/wf[@wid='#{target_ids.first}']")
-        .first
-        .get('sent')
-      end
-
-      ##
-      # Checks if a term is an intensifier.
-      #
-      # @return [TrueClass|FalseClass]
-      #
-      def is_intensifier?
-        sentiment_modifier == "intensifier"
-      end
-
-      ##
-      # Checks if a term is a shifter.
-      #
-      # @return [TrueClass|FalseClass]
-      #
-      def is_shifter?
-        sentiment_modifier == "shifter"
-      end
-
-      ##
-      # Checks if a term is an expression.
-      #
-      # @return [TrueClass|FalseClass]
-      #
-      def is_expression?
-        use && !!polarity
-      end
-
-      ##
-      # Checks if a term is a conjunction.
-      #
-      # @return [TrueClass|FalseClass]
-      #
-      def is_conjunction?(language)
-        pos == 'J' || CONJUNCTIONS[language]&.include?(lemma)
-      end
-
-      private
-
-      # @return [Oga::XML::Element]
-      def first_sentiment
-        @first_sentiment ||= node.xpath('sentiment').first
-      end
-    end # Term
-  end # OpinionDetectorBasic
-end # Opener