treat 0.1.4 → 0.2.0

data/test/tc_resources.rb

@@ -3,8 +3,8 @@ module Treat
     class TestLanguages < Test::Unit::TestCase
 
       def test_languages
-        assert_equal :eng, Treat::Languages.find(:english, 2)
-        assert_equal :en, Treat::Languages.find(:english, 1)
+        assert_equal :eng, Treat::Languages.code(:english, 2)
+        assert_equal :en, Treat::Languages.code(:english, 1)
         assert_equal :english, Treat::Languages.describe(:eng)
         assert_equal :english, Treat::Languages.describe(:en)
       end
@@ -17,11 +17,6 @@ module Treat
         
       end
       
-      def test_edges
-        
-      end
-      
     end
-
   end
 end

data/test/tc_treat.rb

@@ -1,10 +1,10 @@
 module Treat
   module Tests
     class TestTreat < Test::Unit::TestCase
-      
+
       def test_edulcoration
-        Treat.edulcorate
-        assert_equal true, Treat.edulcorated?
+        Treat.sweeten!
+        assert_equal true, Treat.sweetened?
         Treat::Entities.list.each do |klass|
           next if klass == :symbol
           assert_nothing_raised do
@@ -16,9 +16,9 @@ module Treat
               raise
             end
           end
-        end 
-        Treat.unedulcorate
-        assert_equal false, Treat.edulcorated?
+        end
+        Treat.unsweeten!
+        assert_equal false, Treat.sweetened?
         Treat::Entities.list.each do |klass|
           next if klass == :symbol
           assert_raise(NoMethodError) do
@@ -26,37 +26,35 @@ module Treat
           end
         end
       end
-      
+
       def test_modules_loaded?
         ['exception',
-        'languages',
-        'entities',
-        'feature',
-        'category',
-        'group',
-        'detectors',
-        'formatters',
-        'processors',
-        'lexicalizers',
-        'extractors',
-        'inflectors',
+          'languages',
+          'entities',
+          'feature',
+          'category',
+          'group',
+          'formatters',
+          'processors',
+          'lexicalizers',
+          'extractors',
+          'inflectors',
         'proxies'].each do |klass|
           assert_nothing_raised do
             Treat.const_get klass.capitalize
           end
         end
       end
-      
+
       def test_paths
         assert_not_nil Treat.lib
-        assert_not_nil Treat.bin
         assert_not_nil Treat.test
       end
-      
+
       def test_file_permissions
         assert_equal true, File.writable?(Treat.lib + '/../tmp')
       end
-      
+
     end
   end
 end

data/test/tc_tree.rb

@@ -8,7 +8,7 @@ module Treat
         @leaf = Treat::Tree::Node.new('leaf node', 'leaf')
         @root << @branch << @leaf
         @root << @sibling
-        @leaf.associate(@sibling, 'some dependency')
+        @leaf.link(@sibling, 'some dependency')
       end
       def test_branching
         assert_equal 2, @root.children.size
@@ -50,9 +50,9 @@ module Treat
         assert_equal true, @branch.has_parent?
         assert_equal true, @leaf.has_parent?
         
-        assert_equal false, @root.has_edges?
-        assert_equal false, @branch.has_edges?
-        assert_equal true, @leaf.has_edges?
+        assert_equal false, @root.has_dependencies?
+        assert_equal false, @branch.has_dependencies?
+        assert_equal true, @leaf.has_dependencies?
         
       end
     end

data/test/tests.rb

@@ -4,19 +4,17 @@ $:.unshift File.join(File.dirname(__FILE__), "..", "lib")
 
 require 'treat'
 
-# $LOAD_PATH << '/ruby/treat/test' # Remove for release
-# Treat.bin = '/ruby/nat/bin' # Remove for release
+#$LOAD_PATH << '/ruby/gems/treat/test' # Remove for release
 
 require 'texts'
 
+# This is roughly in order of dependence.
 require 'tc_treat'
 require 'tc_tree'
 require 'tc_entity'
 require 'tc_resources'
-
-require 'tc_detectors'
 require 'tc_formatters'
 require 'tc_inflectors'
 require 'tc_lexicalizers'
 require 'tc_processors'
-require 'tc_extractors'
+#require 'tc_extractors'

data/test/texts.rb

@@ -1,20 +1,19 @@
 module Treat
   module Tests
 
-    EnglishHtmlDoc = Treat::Entities::Document("#{Treat.test}/texts/english/long.html")
-    EnglishLongDoc = Treat::Entities::Document("#{Treat.test}/texts/english/long.txt")    
-    EnglishMediumDoc = Treat::Entities::Document("#{Treat.test}/texts/english/medium.txt")  
-    EnglishShortDoc = Treat::Entities::Document("#{Treat.test}/texts/english/short.txt")
-      
-    EnglishTime = Treat::Entities::Phrase('5 PM')
-    EnglishDate = Treat::Entities::Phrase('this tuesday')
-    
-    EnglishSentence = Treat::Entities::Sentence('The quick brown fox jumped over the lazy dog.')
-    
-    EnglishVerb = Treat::Entities::Word('run'); EnglishVerb.set :category, :verb
-    EnglishWord = Treat::Entities::Word('running')
-    EnglishNoun = Treat::Entities::Word('captain')
-    Number = Treat::Entities::Number(20)
+    module English
+      Collection = Treat::Entities::Collection "#{Treat.test}/texts/english"
+      LongDoc = Treat::Entities::Document "#{Treat.test}/texts/english/long.txt"
+      MediumDoc = Treat::Entities::Document "#{Treat.test}/texts/english/medium.txt"
+      ShortDoc = Treat::Entities::Document "#{Treat.test}/texts/english/short.txt"
+      Time = Treat::Entities::Phrase 'every Tuesday at 3:00'
+      Date = Treat::Entities::Phrase '2011/02/01'
+      Sentence = Treat::Entities::Sentence 'The quick brown fox jumped over the lazy dog.'
+      Verb = Treat::Entities::Word 'run'
+      Word = Treat::Entities::Word 'running'
+      Noun = Treat::Entities::Word 'captain'
+      Number = Treat::Entities::Number 20
+    end
     
   end
 end

data/tmp/INFO

@@ -0,0 +1 @@
+This is a folder for temporary files created by Treat.

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: treat
 version: !ruby/object:Gem::Version
-  version: 0.1.4
+  version: 0.2.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-01-26 00:00:00.000000000 Z
+date: 2012-02-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rjb
-  requirement: &70243259830940 !ruby/object:Gem::Requirement
+  requirement: &70310096172480 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -21,21 +21,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70243259830940
+  version_requirements: *70310096172480
 - !ruby/object:Gem::Dependency
-  name: nokogiri
-  requirement: &70243259829420 !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: *70243259829420
-- !ruby/object:Gem::Dependency
-  name: chronic
-  requirement: &70243259828180 !ruby/object:Gem::Requirement
+  name: zip
+  requirement: &70310096171240 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -43,10 +32,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70243259828180
+  version_requirements: *70310096171240
 - !ruby/object:Gem::Dependency
   name: hpricot
-  requirement: &70243259826580 !ruby/object:Gem::Requirement
+  requirement: &70310096170020 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -54,10 +43,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70243259826580
+  version_requirements: *70310096170020
 - !ruby/object:Gem::Dependency
-  name: psych
-  requirement: &70243259824560 !ruby/object:Gem::Requirement
+  name: nokogiri
+  requirement: &70310096168860 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -65,10 +54,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70243259824560
+  version_requirements: *70310096168860
 - !ruby/object:Gem::Dependency
-  name: rchardet19
-  requirement: &70243259839300 !ruby/object:Gem::Requirement
+  name: psych
+  requirement: &70310096166960 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -76,43 +65,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70243259839300
+  version_requirements: *70310096166960
 - !ruby/object:Gem::Dependency
   name: whatlanguage
-  requirement: &70243259837640 !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: *70243259837640
-- !ruby/object:Gem::Dependency
-  name: wordnet
-  requirement: &70243259835240 !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: *70243259835240
-- !ruby/object:Gem::Dependency
-  name: rbtagger
-  requirement: &70243259832320 !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: *70243259832320
-- !ruby/object:Gem::Dependency
-  name: engtagger
-  requirement: &70243259839180 !ruby/object:Gem::Requirement
+  requirement: &70310096163460 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -120,54 +76,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70243259839180
-- !ruby/object:Gem::Dependency
-  name: punkt-segmenter
-  requirement: &70243259836880 !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: *70243259836880
-- !ruby/object:Gem::Dependency
-  name: tokenizer
-  requirement: &70243259834100 !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: *70243259834100
-- !ruby/object:Gem::Dependency
-  name: tactful_tokenizer
-  requirement: &70243259830340 !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: *70243259830340
-- !ruby/object:Gem::Dependency
-  name: english
-  requirement: &70243259828860 !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: *70243259828860
+  version_requirements: *70310096163460
 - !ruby/object:Gem::Dependency
   name: linguistics
-  requirement: &70243259827140 !ruby/object:Gem::Requirement
+  requirement: &70310096159580 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -175,10 +87,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70243259827140
+  version_requirements: *70310096159580
 - !ruby/object:Gem::Dependency
-  name: ruby-stemmer
-  requirement: &70243259824840 !ruby/object:Gem::Requirement
+  name: stanford-core-nlp
+  requirement: &70310096158080 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -186,10 +98,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70243259824840
+  version_requirements: *70310096158080
 - !ruby/object:Gem::Dependency
-  name: uea-stemmer
-  requirement: &70243259812140 !ruby/object:Gem::Requirement
+  name: punkt-segmenter
+  requirement: &70310096156900 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -197,10 +109,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70243259812140
+  version_requirements: *70310096156900
 - !ruby/object:Gem::Dependency
   name: lda-ruby
-  requirement: &70243259810000 !ruby/object:Gem::Requirement
+  requirement: &70310096155740 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -208,10 +120,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70243259810000
+  version_requirements: *70310096155740
 - !ruby/object:Gem::Dependency
-  name: nickel
-  requirement: &70243259808300 !ruby/object:Gem::Requirement
+  name: chronic
+  requirement: &70310096154280 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -219,18 +131,7 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70243259808300
-- !ruby/object:Gem::Dependency
-  name: unprof
-  requirement: &70243259805800 !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: *70243259805800
+  version_requirements: *70310096154280
 description: ! ' Treat is a toolkit for text retrieval, information extraction and
   natural language processing. '
 email:
@@ -239,35 +140,40 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- lib/economist/half_cocked_basel.txt
+- lib/economist/hose_and_dry.doc
+- lib/economist/hungarys_troubles.abw
+- lib/economist/republican_nomination.pdf
+- lib/economist/saving_the_euro.odt
+- lib/economist/to_infinity_and_beyond.txt
+- lib/economist/zero_sum.html
 - lib/treat/buildable.rb
 - lib/treat/categories.rb
 - lib/treat/category.rb
 - lib/treat/delegatable.rb
-- lib/treat/detectors/encoding/r_chardet19.rb
-- lib/treat/detectors/format/file.rb
-- lib/treat/detectors/language/language_detector.rb
-- lib/treat/detectors/language/what_language.rb
-- lib/treat/detectors.rb
+- lib/treat/doable.rb
 - lib/treat/entities/collection.rb
-- lib/treat/entities/constituents.rb
 - lib/treat/entities/document.rb
 - lib/treat/entities/entity.rb
-- lib/treat/entities/sentence.rb
+- lib/treat/entities/phrases.rb
 - lib/treat/entities/tokens.rb
 - lib/treat/entities/zones.rb
 - lib/treat/entities.rb
 - lib/treat/exception.rb
-- lib/treat/extractors/keywords/topics_frequency.rb
-- lib/treat/extractors/named_entity/abner.rb
-- lib/treat/extractors/named_entity/stanford.rb
+- lib/treat/extractors/coreferences/stanford.rb
+- lib/treat/extractors/date/chronic.rb
+- lib/treat/extractors/date/ruby.rb
+- lib/treat/extractors/keywords/tf_idf.rb
+- lib/treat/extractors/keywords/topics_tf_idf.rb
+- lib/treat/extractors/language/language_extractor.rb
+- lib/treat/extractors/language/what_language.rb
+- lib/treat/extractors/named_entity_tag/stanford.rb
+- lib/treat/extractors/roles/naive.rb
 - lib/treat/extractors/statistics/frequency_in.rb
-- lib/treat/extractors/statistics/frequency_of.rb
-- lib/treat/extractors/statistics/position_in_parent.rb
+- lib/treat/extractors/statistics/position_in.rb
 - lib/treat/extractors/statistics/tf_idf.rb
 - lib/treat/extractors/statistics/transition_matrix.rb
 - lib/treat/extractors/statistics/transition_probability.rb
-- lib/treat/extractors/time/chronic.rb
-- lib/treat/extractors/time/native.rb
 - lib/treat/extractors/time/nickel.rb
 - lib/treat/extractors/topic_words/lda/data.dat
 - lib/treat/extractors/topic_words/lda/wiki.yml
@@ -278,63 +184,79 @@ files:
 - lib/treat/extractors/topics/reuters.rb
 - lib/treat/extractors.rb
 - lib/treat/feature.rb
+- lib/treat/features.rb
 - lib/treat/formatters/readers/abw.rb
 - lib/treat/formatters/readers/autoselect.rb
 - lib/treat/formatters/readers/doc.rb
-- lib/treat/formatters/readers/gocr.rb
 - lib/treat/formatters/readers/html.rb
-- lib/treat/formatters/readers/ocropus.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/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/html.rb
-- lib/treat/formatters/visualizers/inspect.rb
 - lib/treat/formatters/visualizers/short_value.rb
 - lib/treat/formatters/visualizers/standoff.rb
 - lib/treat/formatters/visualizers/tree.rb
 - lib/treat/formatters/visualizers/txt.rb
 - lib/treat/formatters.rb
 - lib/treat/group.rb
+- lib/treat/helpers/linguistics_loader.rb
 - lib/treat/inflectors/cardinal_words/linguistics.rb
 - lib/treat/inflectors/conjugations/linguistics.rb
-- lib/treat/inflectors/declensions/en.rb
+- lib/treat/inflectors/declensions/english.rb
 - lib/treat/inflectors/declensions/linguistics.rb
 - lib/treat/inflectors/ordinal_words/linguistics.rb
 - lib/treat/inflectors/stem/porter.rb
 - lib/treat/inflectors/stem/porter_c.rb
 - lib/treat/inflectors/stem/uea.rb
 - lib/treat/inflectors.rb
+- lib/treat/install.rb
 - lib/treat/kernel.rb
 - lib/treat/languages/arabic.rb
-- lib/treat/languages/categories.rb
 - lib/treat/languages/chinese.rb
-- lib/treat/languages/english/categories.rb
-- lib/treat/languages/english/tags.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/list.txt
-- lib/treat/languages/xinhua.rb
+- 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/tags.rb
 - lib/treat/languages.rb
 - lib/treat/lexicalizers/category/from_tag.rb
 - lib/treat/lexicalizers/linkages/naive.rb
-- lib/treat/lexicalizers/synsets/rita_wn.rb
 - lib/treat/lexicalizers/synsets/wordnet.rb
 - lib/treat/lexicalizers/tag/brill.rb
 - lib/treat/lexicalizers/tag/lingua.rb
 - lib/treat/lexicalizers/tag/stanford.rb
+- lib/treat/lexicalizers/tag/tagger.rb
 - lib/treat/lexicalizers.rb
 - lib/treat/object.rb
 - lib/treat/processors/chunkers/txt.rb
 - lib/treat/processors/parsers/enju.rb
 - lib/treat/processors/parsers/stanford.rb
+- lib/treat/processors/segmenters/punkt/dutch.yaml
+- lib/treat/processors/segmenters/punkt/english.yaml
+- lib/treat/processors/segmenters/punkt/french.yaml
+- lib/treat/processors/segmenters/punkt/german.yaml
+- lib/treat/processors/segmenters/punkt/greek.yaml
+- lib/treat/processors/segmenters/punkt/italian.yaml
+- lib/treat/processors/segmenters/punkt/polish.yaml
+- lib/treat/processors/segmenters/punkt/portuguese.yaml
+- lib/treat/processors/segmenters/punkt/russian.yaml
+- lib/treat/processors/segmenters/punkt/spanish.yaml
+- lib/treat/processors/segmenters/punkt/swedish.yaml
 - lib/treat/processors/segmenters/punkt.rb
 - lib/treat/processors/segmenters/stanford.rb
 - lib/treat/processors/segmenters/tactful.rb
@@ -347,13 +269,12 @@ files:
 - lib/treat/processors.rb
 - lib/treat/proxies.rb
 - lib/treat/registrable.rb
-- lib/treat/string.rb
 - lib/treat/sugar.rb
 - lib/treat/tree.rb
+- lib/treat/viewable.rb
 - lib/treat/visitable.rb
 - lib/treat.rb
 - test/profile.rb
-- test/tc_detectors.rb
 - test/tc_entity.rb
 - test/tc_extractors.rb
 - test/tc_formatters.rb
@@ -375,9 +296,7 @@ files:
 - test/texts/english/short.txt
 - test/texts/english/zero_sum.html
 - test/texts.rb
-- examples/benchmark.rb
-- examples/keywords.rb
-- bin/INFO
+- tmp/INFO
 - README
 - TODO
 - LICENSE
@@ -407,3 +326,4 @@ signing_key:
 specification_version: 3
 summary: Text retrieval, extraction and annotation toolkit
 test_files: []
+has_rdoc: