treat 1.0.6 → 1.1.0

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: treat
 version: !ruby/object:Gem::Version
-  version: 1.0.6
+  version: 1.1.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,16 +9,16 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-05-22 00:00:00.000000000 Z
+date: 2012-07-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: rubyzip
+  name: schiphol
   requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: 0.9.6.1
+        version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -26,23 +26,7 @@ dependencies:
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: 0.9.6.1
-- !ruby/object:Gem::Dependency
-  name: progressbar
-  requirement: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: 0.10.0
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: 0.10.0
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
@@ -50,7 +34,7 @@ dependencies:
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: 2.9.0
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -58,7 +42,7 @@ dependencies:
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: 2.9.0
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -66,7 +50,7 @@ dependencies:
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: 0.9.2
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -74,26 +58,66 @@ dependencies:
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: 0.9.2
-description: ! ' Treat is a full-fledged natural language processing toolkit for Ruby. '
+        version: '0'
+description: ! ' Treat is a natural language processing framework for Ruby. '
 email:
 - louis.mullie@gmail.com
 executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- lib/treat/ai/classifiers/id3.rb
-- lib/treat/ai/classifiers/mlp.rb
-- lib/treat/ai.rb
-- lib/treat/categories.rb
-- lib/treat/categorizable.rb
-- lib/treat/classification.rb
-- lib/treat/configurable.rb
-- lib/treat/data_set.rb
-- lib/treat/dependencies.rb
-- lib/treat/downloader.rb
+- bin/MANIFEST
+- bin/stanford/bridge.jar
+- bin/stanford/joda-time.jar
+- bin/stanford/stanford-corenlp.jar
+- bin/stanford/stanford-parser.jar
+- bin/stanford/xom.jar
+- lib/treat/config/core/acronyms.rb
+- lib/treat/config/core/encodings.rb
+- lib/treat/config/core/entities.rb
+- lib/treat/config/core/language.rb
+- lib/treat/config/core/paths.rb
+- lib/treat/config/core/syntax.rb
+- lib/treat/config/core/verbosity.rb
+- lib/treat/config/databases/mongo.rb
+- lib/treat/config/languages/agnostic.rb
+- lib/treat/config/languages/arabic.rb
+- lib/treat/config/languages/chinese.rb
+- lib/treat/config/languages/dutch.rb
+- lib/treat/config/languages/english.rb
+- lib/treat/config/languages/french.rb
+- lib/treat/config/languages/german.rb
+- lib/treat/config/languages/greek.rb
+- lib/treat/config/languages/italian.rb
+- lib/treat/config/languages/polish.rb
+- lib/treat/config/languages/portuguese.rb
+- lib/treat/config/languages/russian.rb
+- lib/treat/config/languages/spanish.rb
+- lib/treat/config/languages/swedish.rb
+- lib/treat/config/libraries/stanford.rb
+- lib/treat/config/linguistics/categories.rb
+- lib/treat/config/linguistics/punctuation.rb
+- lib/treat/config/tags/aligned.rb
+- lib/treat/config/tags/enju.rb
+- lib/treat/config/tags/paris7.rb
+- lib/treat/config/tags/ptb.rb
+- lib/treat/config/workers/extractors.rb
+- lib/treat/config/workers/formatters.rb
+- lib/treat/config/workers/inflectors.rb
+- lib/treat/config/workers/learners.rb
+- lib/treat/config/workers/lexicalizers.rb
+- lib/treat/config/workers/list.rb
+- lib/treat/config/workers/processors.rb
+- lib/treat/config/workers/retrievers.rb
+- lib/treat/config.rb
+- lib/treat/core/classification.rb
+- lib/treat/core/data_set.rb
+- lib/treat/core/node.rb
+- lib/treat/core/server.rb
+- lib/treat/core.rb
 - lib/treat/entities/abilities/buildable.rb
 - lib/treat/entities/abilities/checkable.rb
+- lib/treat/entities/abilities/comparable.rb
 - lib/treat/entities/abilities/copyable.rb
 - lib/treat/entities/abilities/countable.rb
 - lib/treat/entities/abilities/debuggable.rb
@@ -104,109 +128,96 @@ files:
 - lib/treat/entities/abilities/magical.rb
 - lib/treat/entities/abilities/registrable.rb
 - lib/treat/entities/abilities/stringable.rb
-- lib/treat/entities/abilities.rb
-- lib/treat/entities/entities.rb
+- lib/treat/entities/collection.rb
+- lib/treat/entities/document.rb
 - lib/treat/entities/entity.rb
+- lib/treat/entities/group.rb
+- lib/treat/entities/section.rb
+- lib/treat/entities/token.rb
+- lib/treat/entities/zone.rb
 - lib/treat/entities.rb
-- lib/treat/exception.rb
-- lib/treat/extractors/keywords/tf_idf.rb
-- lib/treat/extractors/language/what_language.rb
-- lib/treat/extractors/name_tag/stanford.rb
-- lib/treat/extractors/tf_idf/native.rb
-- lib/treat/extractors/time/chronic.rb
-- lib/treat/extractors/time/nickel.rb
-- lib/treat/extractors/time/ruby.rb
-- lib/treat/extractors/topic_words/lda.rb
-- lib/treat/extractors/topics/reuters.rb
-- lib/treat/extractors.rb
-- lib/treat/formatters/readers/abw.rb
-- lib/treat/formatters/readers/autoselect.rb
-- lib/treat/formatters/readers/doc.rb
-- lib/treat/formatters/readers/html.rb
-- lib/treat/formatters/readers/image.rb
-- lib/treat/formatters/readers/odt.rb
-- lib/treat/formatters/readers/pdf.rb
-- lib/treat/formatters/readers/txt.rb
-- lib/treat/formatters/readers/xml.rb
-- lib/treat/formatters/serializers/mongo.rb
-- lib/treat/formatters/serializers/xml.rb
-- lib/treat/formatters/serializers/yaml.rb
-- lib/treat/formatters/unserializers/autoselect.rb
-- lib/treat/formatters/unserializers/xml.rb
-- lib/treat/formatters/unserializers/yaml.rb
-- lib/treat/formatters/visualizers/dot.rb
-- lib/treat/formatters/visualizers/standoff.rb
-- lib/treat/formatters/visualizers/tree.rb
-- lib/treat/formatters.rb
-- lib/treat/groupable.rb
-- lib/treat/helpers/decimal_point_escaper.rb
-- lib/treat/inflectors/cardinalizers/linguistics.rb
-- lib/treat/inflectors/conjugators/linguistics.rb
-- lib/treat/inflectors/declensors/active_support.rb
-- lib/treat/inflectors/declensors/english/inflect.rb
-- lib/treat/inflectors/declensors/english.rb
-- lib/treat/inflectors/declensors/linguistics.rb
-- lib/treat/inflectors/ordinalizers/linguistics.rb
-- lib/treat/inflectors/stemmers/porter.rb
-- lib/treat/inflectors/stemmers/porter_c.rb
-- lib/treat/inflectors/stemmers/uea.rb
-- lib/treat/inflectors.rb
+- lib/treat/helpers/didyoumean.rb
+- lib/treat/helpers/escaping.rb
+- lib/treat/helpers/formatting.rb
+- lib/treat/helpers/platform.rb
+- lib/treat/helpers/reflection.rb
+- lib/treat/helpers/temporary.rb
+- lib/treat/helpers/verbosity.rb
+- lib/treat/helpers.rb
 - lib/treat/installer.rb
-- lib/treat/kernel.rb
-- lib/treat/languages/arabic.rb
-- lib/treat/languages/chinese.rb
-- lib/treat/languages/dutch.rb
-- lib/treat/languages/english.rb
-- lib/treat/languages/french.rb
-- lib/treat/languages/german.rb
-- lib/treat/languages/greek.rb
-- lib/treat/languages/italian.rb
-- lib/treat/languages/language.rb
-- lib/treat/languages/list.txt
-- lib/treat/languages/polish.rb
-- lib/treat/languages/portuguese.rb
-- lib/treat/languages/russian.rb
-- lib/treat/languages/spanish.rb
-- lib/treat/languages/swedish.rb
-- lib/treat/languages.rb
-- lib/treat/lexicalizers/categorizers/from_tag.rb
-- lib/treat/lexicalizers/sensers/wordnet/synset.rb
-- lib/treat/lexicalizers/sensers/wordnet.rb
-- lib/treat/lexicalizers/taggers/brill/patch.rb
-- lib/treat/lexicalizers/taggers/brill.rb
-- lib/treat/lexicalizers/taggers/lingua.rb
-- lib/treat/lexicalizers/taggers/stanford.rb
-- lib/treat/lexicalizers.rb
 - lib/treat/loaders/linguistics.rb
 - lib/treat/loaders/stanford.rb
-- lib/treat/object.rb
-- lib/treat/processors/chunkers/autoselect.rb
-- lib/treat/processors/chunkers/html.rb
-- lib/treat/processors/chunkers/txt.rb
-- lib/treat/processors/parsers/enju.rb
-- lib/treat/processors/parsers/stanford.rb
-- lib/treat/processors/segmenters/punkt.rb
-- lib/treat/processors/segmenters/stanford.rb
-- lib/treat/processors/segmenters/tactful.rb
-- lib/treat/processors/tokenizers/ptb.rb
-- lib/treat/processors/tokenizers/punkt.rb
-- lib/treat/processors/tokenizers/stanford.rb
-- lib/treat/processors/tokenizers/tactful.rb
-- lib/treat/processors.rb
+- lib/treat/loaders.rb
 - lib/treat/proxies.rb
-- lib/treat/retrievers/indexers/ferret.rb
-- lib/treat/retrievers/searchers/ferret.rb
-- lib/treat/retrievers.rb
-- lib/treat/server.rb
-- lib/treat/tree.rb
-- lib/treat/universalisation/encodings.rb
-- lib/treat/universalisation/tags.rb
-- lib/treat/universalisation.rb
+- lib/treat/version.rb
+- lib/treat/workers/extractors/keywords/tf_idf.rb
+- lib/treat/workers/extractors/language/what_language.rb
+- lib/treat/workers/extractors/name_tag/stanford.rb
+- lib/treat/workers/extractors/tf_idf/native.rb
+- lib/treat/workers/extractors/time/chronic.rb
+- lib/treat/workers/extractors/time/nickel.rb
+- lib/treat/workers/extractors/time/ruby.rb
+- lib/treat/workers/extractors/topic_words/lda.rb
+- lib/treat/workers/extractors/topics/reuters.rb
+- lib/treat/workers/formatters/readers/abw.rb
+- lib/treat/workers/formatters/readers/autoselect.rb
+- lib/treat/workers/formatters/readers/doc.rb
+- lib/treat/workers/formatters/readers/html.rb
+- lib/treat/workers/formatters/readers/image.rb
+- lib/treat/workers/formatters/readers/odt.rb
+- lib/treat/workers/formatters/readers/pdf.rb
+- lib/treat/workers/formatters/readers/txt.rb
+- lib/treat/workers/formatters/readers/xml.rb
+- lib/treat/workers/formatters/serializers/mongo.rb
+- lib/treat/workers/formatters/serializers/xml.rb
+- lib/treat/workers/formatters/serializers/yaml.rb
+- lib/treat/workers/formatters/unserializers/autoselect.rb
+- lib/treat/workers/formatters/unserializers/mongo.rb
+- lib/treat/workers/formatters/unserializers/xml.rb
+- lib/treat/workers/formatters/unserializers/yaml.rb
+- lib/treat/workers/formatters/visualizers/dot.rb
+- lib/treat/workers/formatters/visualizers/standoff.rb
+- lib/treat/workers/formatters/visualizers/tree.rb
+- lib/treat/workers/group.rb
+- lib/treat/workers/inflectors/cardinalizers/linguistics.rb
+- lib/treat/workers/inflectors/conjugators/linguistics.rb
+- lib/treat/workers/inflectors/declensors/active_support.rb
+- lib/treat/workers/inflectors/declensors/english/inflect.rb
+- lib/treat/workers/inflectors/declensors/english.rb
+- lib/treat/workers/inflectors/declensors/linguistics.rb
+- lib/treat/workers/inflectors/ordinalizers/linguistics.rb
+- lib/treat/workers/inflectors/stemmers/porter.rb
+- lib/treat/workers/inflectors/stemmers/porter_c.rb
+- lib/treat/workers/inflectors/stemmers/uea.rb
+- lib/treat/workers/learners/classifiers/id3.rb
+- lib/treat/workers/learners/classifiers/mlp.rb
+- lib/treat/workers/lexicalizers/categorizers/from_tag.rb
+- lib/treat/workers/lexicalizers/sensers/wordnet/synset.rb
+- lib/treat/workers/lexicalizers/sensers/wordnet.rb
+- lib/treat/workers/lexicalizers/taggers/brill/patch.rb
+- lib/treat/workers/lexicalizers/taggers/brill.rb
+- lib/treat/workers/lexicalizers/taggers/lingua.rb
+- lib/treat/workers/lexicalizers/taggers/stanford.rb
+- lib/treat/workers/processors/chunkers/autoselect.rb
+- lib/treat/workers/processors/chunkers/html.rb
+- lib/treat/workers/processors/chunkers/txt.rb
+- lib/treat/workers/processors/parsers/enju.rb
+- lib/treat/workers/processors/parsers/stanford.rb
+- lib/treat/workers/processors/segmenters/punkt.rb
+- lib/treat/workers/processors/segmenters/stanford.rb
+- lib/treat/workers/processors/segmenters/tactful.rb
+- lib/treat/workers/processors/tokenizers/ptb.rb
+- lib/treat/workers/processors/tokenizers/punkt.rb
+- lib/treat/workers/processors/tokenizers/stanford.rb
+- lib/treat/workers/processors/tokenizers/tactful.rb
+- lib/treat/workers/retrievers/indexers/ferret.rb
+- lib/treat/workers/retrievers/searchers/ferret.rb
+- lib/treat/workers.rb
 - lib/treat.rb
 - spec/collection.rb
 - spec/document.rb
 - spec/entity.rb
-- spec/languages.rb
+- spec/node.rb
 - spec/phrase.rb
 - spec/samples/mathematicians/archimedes.abw
 - spec/samples/mathematicians/euler.html
@@ -216,21 +227,20 @@ files:
 - spec/sandbox.rb
 - spec/token.rb
 - spec/treat.rb
-- spec/tree.rb
 - spec/word.rb
 - spec/zone.rb
-- tmp/INFO
-- files/guides.rubyonrails.org/3_2_release_notes.html
-- files/INFO
-- files/www.economist.com/21552208
-- files/www.rubyinside.com/nethttp-cheat-sheet-2940.html
+- tmp/english.yaml
+- tmp/MANIFEST
+- files/21552208.html
+- files/3_2_release_notes.html
+- files/MANIFEST
+- files/nethttp-cheat-sheet-2940.html
+- files/weather-central-canada-heat-wave.html
 - README.md
 - LICENSE
 homepage: https://github.com/louismullie/treat
 licenses: []
-post_install_message: ! "********************************************************************************\n\nThank
-  you for installing Treat!\n\nComplete the installation by running:\n\n    require
-  'treat'\n    Treat.install\n\ninside IRB or a Ruby script.\n\n********************************************************************************\n\n"
+post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
@@ -248,7 +258,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.21
+rubygems_version: 1.8.24
 signing_key: 
 specification_version: 3
 summary: Text Retrieval, Extraction and Annotation Toolkit.

data/lib/treat/ai.rb

@@ -1,12 +0,0 @@
-module Treat::AI
-  
-  module Classifiers
-    extend Treat::Groupable
-    self.type = :computer
-    self.targets = [:entity]
-    self.default = :id3
-  end
-  
-  extend Treat::Categorizable
-  
-end

data/lib/treat/categories.rb

@@ -1,90 +0,0 @@
-# This module keeps track of all the Treat::Categorizable
-# modules that exist and the methods they define.
-#
-#
-# - Processors perform the building of tree of
-#   entities representing texts (chunking,
-#   segmenting, tokenizing, parsing).
-# - Lexicalizers give lexical information about
-#   words (synsets, semantic relationships,
-#   tag, word category).
-# - Extractors extract semantic information about
-#   an entity (language, topic, date, time, named
-#   entity, coreferences).
-# - Inflectors allow to retrieve the different
-#   inflections of a word (declensors, conjugators,
-#   stemmers, lemmatizers).
-# - Formatters handle the conversion of entities to
-#   and from different formats(readers, serializers,
-#   unserializers, visualizers).
-# - Retrievers allow to index and search collections
-#   of documents.
-module Treat::Categories
-
-  class << self
-    # A list of all categories.
-    attr_accessor :list
-  end
-
-  # Array - list of all categories.
-  self.list = []
-  # A lookup table for entity types.
-  @@lookup = {}
-
-  # Require all categories.
-  require 'treat/categorizable'
-  require 'treat/formatters'
-  require 'treat/processors'
-  require 'treat/lexicalizers'
-  require 'treat/inflectors'
-  require 'treat/extractors'
-  require 'treat/retrievers'
-  require 'treat/ai'
-  
-  # Create the lookup table.
-  self.list.each do |category|
-    category.groups.each do |group|
-      group = category.const_get(group)
-      @@lookup[group.method] = group
-      group.presets.each do |x,y|
-        @@lookup[x] = group
-      end if group.presets
-    end
-  end
-
-  # Find the class of a group given its method.
-  def self.lookup(method)
-    @@lookup[method]
-  end
-
-  # Fix -- This must be moved urgently.
-  Treat::Entities::Entity.class_eval do
-
-    alias :true_language :language
-    
-    def language(extractor = nil, options = {})
-      
-      if is_a?(Treat::Entities::Symbol) ||
-        is_a?(Treat::Entities::Number)
-        return Treat.default_language
-      end
-      
-      if !Treat.detect_language
-        return Treat.default_language
-      else
-        dlvl = Treat.language_detection_level
-        if (Treat::Entities.rank(type) <
-          Treat::Entities.rank(dlvl)) &&
-          has_parent?
-          anc = ancestor_with_type(dlvl)
-          return anc.language if anc
-        end
-      end
-      
-      true_language(extractor, options)
-      
-    end
-
-  end
-
-end

data/lib/treat/categorizable.rb

@@ -1,44 +0,0 @@
-# A categorizable module brings together groups 
-# of algorithms that perform similar functions.
-module Treat::Categorizable
-  
-  # The contents of each categorizable 
-  # module are groupable.
-  require 'treat/groupable'
-  
-  # Add workers to the Entities based on the
-  # configuration for a given category.
-  def self.extended(category)
-    Treat::Categories.list << category
-    category.module_eval do
-      groups.each do |group|
-        group = const_get(group)
-        group.targets.each do |entity_type|
-          entity = Treat::Entities.
-          const_get(cc(entity_type))
-          entity.class_eval do
-            add_workers group
-          end
-        end
-      end
-    end
-  end
-  
-  # Get the list of groups defined
-  # under this module.
-  @@groups = self.constants
-  
-  # Populate a list of methods.
-  @@methods = []
-  @@groups.each do |group|
-    @@methods << const_get(group).method
-  end
-  
-  # Provide a list of methods implemented in
-  # the groups contained within this category.
-  def methods; @@methods; end
-  
-  # Provides a list of groups within this category.
-  def groups; self.constants; end
-  
-end

data/lib/treat/configurable.rb

@@ -1,115 +0,0 @@
-# This module provides configuration options for the Treat toolkit
-# (enable/disable syntactic sugar, enable/disable language detection
-# and set default language or language detection level.
-module Treat::Configurable
-
-  # Modify the singleton class of the base module (Treat).
-  def self.extended(base)
-
-    # Configuration options that are available for the Treat module.
-    class << base
-      # Symbol - default language to use when detect_language is false.
-      attr_accessor :default_language
-      # Boolean - detect language or use default?
-      attr_accessor :detect_language
-      # Symbol - the finest entity level at which to detect language.
-      attr_accessor :language_detection_level
-      # Boolean - whether to output debug information or not.
-      attr_accessor :debug
-      # Boolean - whether to silence the output of external programs.
-      attr_accessor :silence
-    end
-
-    # Set the default options.
-    base.module_eval do
-      # Set the default language to english.
-      self.default_language = :eng
-      # Turn language detection off by default.
-      self.detect_language = false
-      # Detect the language once per document by default.
-      self.language_detection_level = :document
-      # Set debug to off by default.
-      self.debug = false
-      # Silence external programs by default.
-      self.silence = true
-    end
-
-  end
-
-  # Turn on syntactic sugar for the creation of Entities.
-  #
-  # All entities found under Treat::Entities will be made
-  # available within the global namespace. As an example,
-  # 'Treat::Entities::Word' can then be referred to as 'Word'.
-  #
-  # There is one exception: the Symbol class is not sweetened
-  # to avoid clashing with the Symbol class defined by Ruby.
-  def sweeten!
-    return if @@sweetened
-    @@sweetened = true
-    each_entity_class do |type, klass|
-      Object.class_eval do
-        unless type == :Symbol
-          define_method(type) do |file_or_value, options={}|
-            klass.build(file_or_value, options)
-          end
-        end
-      end
-    end
-  end
-
-  # Turn off syntactic sugar.
-  def unsweeten!
-    return unless @@sweetened
-    @@sweetened = false
-    each_entity_class do |type, klass|
-      Object.class_eval do
-        remove_method(type)
-      end unless type == :Symbol
-    end
-  end
-
-  # Boolean - whether syntactic sugar is
-  # enabled or not.
-  def sweetened?; @@sweetened; end
-
-  # Syntactic sugar is disabled by default.
-  @@sweetened = false
-
-  # Turn on language detection, optionally setting
-  # the language detection level (finest level at
-  # which language detection is performed).
-  def self.detect!(level = nil)
-    self.detect_language = true
-    if level
-      self.language_detection_level = level
-    end
-  end
-
-  # Turn off language detection, optionally setting
-  # a new default language to use.
-  def self.undetect!(default = :english)
-    self.detect_language = false
-    if default
-      self.default_language = default
-    end
-  end
-
-  # Use the supplied language by default and
-  # turn off language detection.
-  def self.use(language)
-    self.detect_language = false
-    self.default_language = language
-  end
-  
-  private
-  # Helper method, yields each entity type and class.
-  def each_entity_class
-    Treat::Entities.list.each do |entity_type|
-      type = cc(entity_type).intern
-      klass = Treat::Entities.const_get(type, klass)
-      yield type, klass
-    end
-  end
-
-end

data/lib/treat/dependencies.rb

@@ -1,25 +0,0 @@
-class Treat::Dependencies
-  
-  Gem = [
-    ['psych', '>= 1.2.2', '(un)serialize annotated entities to YAML format'],
-    ['nokogiri', '>= 1.5.2', 'read and parse XML and HTML formats'],
-    ['sdsykes-ferret', '>= 0.11.6.19', 'perform full-text search in collections'],
-    ['lda-ruby', '>= 0.3.8', 'extract topic words from documents and collections'],
-    ['ruby-readability', '>= 0.5.2', 'extract the readable content from HTML pages'],
-    ['stanford-core-nlp', '>= 0.3.0', 'tokenize, segment, parse texts and perform named entity recognition'],
-    ['whatlanguage', '>= 1.0.0', 'detect the language of text'],
-    ['linguistics', '>= 1.0.9', 'retrieve the inflection of nouns, verbs and numbers in English'],
-    ['punkt-segmenter', '>= 0.9.1', 'segment texts into sentences'],
-    ['chronic', '>= 0.6.7', 'detect date and time in text'],
-    ['decisiontree', '>= 0.3.0', 'perform decision tree classification of text entities'],
-    ['ai4r', '>= 1.11', 'perform different kinds of classification tasks on text entities']
-  ]
-  
-  Binary = [
-    ['ocropus', 'recognize text in image files'],
-    ['antiword', 'extract text from DOC files'],
-    ['poppler-utils', 'extract text from PDF files'],
-    ['graphviz', 'export and visualize directed graphs']
-  ]
-
-end