treat 0.2.5 → 1.0.0

data/spec/word.rb

@@ -0,0 +1,110 @@
+require_relative '../lib/treat'
+
+describe Treat::Entities::Word do
+
+  describe "Inflectors" do
+
+    before do
+      @inflectors = Treat::Languages::English::Inflectors
+    end
+
+    describe "#stem" do
+
+      it "returns the stem of the word" do
+        @inflectors[:stemmers].each do |s|
+          'running'.stem(s).should eql 'run'
+        end
+      end
+
+    end
+
+    describe "#infinitive" do
+      it "returns the infinitive form of a verb" do
+        @inflectors[:conjugators].each do |c|
+          'running'.infinitive(c).should eql 'run'
+        end
+      end
+    end
+
+    # Nil if not verb?
+    describe "#present_participle" do
+      it "returns the present participle form of a verb" do
+        @inflectors[:conjugators].each do |c|
+          'running'.infinitive(c).should eql 'run'
+        end
+      end
+    end
+
+    describe "#plural" do
+      it "returns the plural form of the word" do
+        @inflectors[:declensors].each do |i|
+          # 'inflection'.plural(i).should eql 'inflections'
+        end
+      end
+    end
+
+    describe "#singular" do
+      it "returns the singular form of the word" do
+        @inflectors[:declensors].each do |i|
+          next if i == :linguistics # Fix this
+          # 'inflections'.singular(i).should eql 'inflections'
+        end
+      end
+    end
+
+    describe "#ordinal_form" do
+      it "returns the ordinal form of a number" do
+        @inflectors[:cardinalizers].each do |o|
+          20.cardinal.should eql 'twenty'
+        end
+        @inflectors[:ordinalizers].each do |o|
+          20.ordinal.should eql 'twentieth'
+        end
+      end
+    end
+
+  end
+
+  describe "Lexicalizable" do
+
+    describe "#synonyms" do
+
+      it "returns the synonyms of the word" do
+        # Should the word be included in synonyms?
+        'glass'.synonyms[-1].should eql 'looking_glass'
+      end
+
+    end
+
+    describe "#antonyms" do
+      it "returns the antonyms of the word" do
+        'glass'.antonyms.should eql []
+      end
+    end
+
+    describe "#hypernyms" do
+      it "returns the hypernyms of the word" do
+        'glass'.hypernyms[-1].should eql 'glasswork'
+      end
+    end
+
+    describe "#hyponyms" do
+      it "returns the hyponyms of the word" do
+        'glass'.hyponyms[-1].should eql 'wineglass'
+      end
+    end
+
+  end
+
+  describe "Extractable" do
+    describe "#tf_idf" do
+      it "returns the TF*IDF score of the word" do
+        #c = Treat::Entities::Collection.build(
+        #Treat.spec + 'samples/mathematicians')
+        #c.do(:chunk, :segment, :tokenize)
+        #c.words[30].tf_idf.should eql 0.2231
+      end
+    end
+  end
+
+end

data/spec/zone.rb

@@ -0,0 +1,66 @@
+require_relative '../lib/treat'
+
+describe Treat::Entities::Zone do
+
+  describe "Processable" do
+
+    describe "#segment" do
+
+      it "splits a zone into phrases/sentences and adds them as children of the zone" do
+        Treat::Languages::English::Processors[:segmenters].each do |s|
+          paragraph = Treat::Entities::Paragraph.new(
+          "This is a first sentence inside the first paragraph. " +
+          "This is the second sentence that is inside the paragraph.")
+          paragraph.segment(s)
+          paragraph.children.should eql paragraph.phrases
+          paragraph.phrases.map { |t| t.to_s }.should
+          eql ["This is a first sentence inside the first paragraph.",
+          "This is the second sentence that is inside the paragraph."]
+        end
+      end
+
+    end
+
+  end
+
+  describe "Buildable" do
+
+    describe "#build" do
+
+      context "when called with a section of text" do
+
+        it "creates a section with the text" do
+
+          section = "A title\nFollowed by a fake sentence."
+          s = Treat::Entities::Zone.build(section)
+          s.should be_an_instance_of Treat::Entities::Section
+
+        end
+
+      end
+
+      context "when called with a paragraph of text" do
+
+        it "creates a paragraph with the text" do
+          paragraph = "Sentence 1. Sentence 2. Sentence 3."
+          p = Treat::Entities::Zone.build(paragraph)
+          p.should be_instance_of Treat::Entities::Paragraph
+        end
+
+      end
+
+      context "when called with a very short text" do
+
+        it "creates a title with the text" do
+          title = "A title!"
+          p = Treat::Entities::Zone.build(title)
+          p.should be_instance_of Treat::Entities::Title
+        end
+
+      end
+
+    end
+    
+  end
+
+end

data/tmp/INFO

@@ -1 +1 @@
-This is a folder for temporary files created by Treat.
+This is a folder containing the temporary files created by Treat.

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: treat
 version: !ruby/object:Gem::Version
-  version: 0.2.5
+  version: 1.0.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,200 +9,116 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-02-07 00:00:00.000000000 Z
+date: 2012-04-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: rjb
-  requirement: &70201865896920 !ruby/object:Gem::Requirement
+  name: rubyzip
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 0.9.6.1
   type: :runtime
   prerelease: false
-  version_requirements: *70201865896920
-- !ruby/object:Gem::Dependency
-  name: zip
-  requirement: &70201865895740 !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: *70201865895740
-- !ruby/object:Gem::Dependency
-  name: hpricot
-  requirement: &70201865893800 !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: *70201865893800
-- !ruby/object:Gem::Dependency
-  name: nokogiri
-  requirement: &70201865892000 !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: *70201865892000
-- !ruby/object:Gem::Dependency
-  name: psych
-  requirement: &70201865889880 !ruby/object:Gem::Requirement
+  version_requirements: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: *70201865889880
+        version: 0.9.6.1
 - !ruby/object:Gem::Dependency
-  name: ferret
-  requirement: &70201865888620 !ruby/object:Gem::Requirement
+  name: progressbar
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 0.10.0
   type: :runtime
   prerelease: false
-  version_requirements: *70201865888620
-- !ruby/object:Gem::Dependency
-  name: whatlanguage
-  requirement: &70201865887460 !ruby/object:Gem::Requirement
+  version_requirements: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: *70201865887460
+        version: 0.10.0
 - !ruby/object:Gem::Dependency
-  name: linguistics
-  requirement: &70201865886480 !ruby/object:Gem::Requirement
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
+        version: 2.9.0
+  type: :development
   prerelease: false
-  version_requirements: *70201865886480
-- !ruby/object:Gem::Dependency
-  name: stanford-core-nlp
-  requirement: &70201865885300 !ruby/object:Gem::Requirement
+  version_requirements: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: *70201865885300
+        version: 2.9.0
 - !ruby/object:Gem::Dependency
-  name: punkt-segmenter
-  requirement: &70201865883560 !ruby/object:Gem::Requirement
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
+        version: 0.9.2
+  type: :development
   prerelease: false
-  version_requirements: *70201865883560
-- !ruby/object:Gem::Dependency
-  name: lda-ruby
-  requirement: &70201865882040 !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: *70201865882040
-- !ruby/object:Gem::Dependency
-  name: chronic
-  requirement: &70201865880540 !ruby/object:Gem::Requirement
+  version_requirements: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: *70201865880540
-description: ! ' Treat is a toolkit for text retrieval, information extraction and
-  natural language processing. '
+        version: 0.9.2
+description: ! ' Treat is a Ruby toolkit for text retrieval, information extraction
+  and natural language processing. '
 email:
 - louis.mullie@gmail.com
 executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- lib/economist/half_cocked_basel.txt
-- lib/economist/hungarys_troubles.txt
-- lib/economist/indias_slowdown.txt
-- lib/economist/merkozy_rides_again.txt
-- lib/economist/prada_is_not_walmart.txt
-- lib/economist/to_infinity_and_beyond.txt
-- lib/ferret/_11.cfs
-- lib/ferret/_14.cfs
-- lib/ferret/_p.cfs
-- lib/ferret/_s.cfs
-- lib/ferret/_v.cfs
-- lib/ferret/_y.cfs
-- lib/ferret/segments
-- lib/ferret/segments_15
-- lib/treat/buildable.rb
+- lib/treat/ai/classifiers/id3.rb
+- lib/treat/ai.rb
 - lib/treat/categories.rb
-- lib/treat/category.rb
-- lib/treat/delegatable.rb
-- lib/treat/doable.rb
-- lib/treat/entities/collection.rb
-- lib/treat/entities/document.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
+- lib/treat/entities/abilities/buildable.rb
+- lib/treat/entities/abilities/checkable.rb
+- lib/treat/entities/abilities/copyable.rb
+- lib/treat/entities/abilities/countable.rb
+- lib/treat/entities/abilities/debuggable.rb
+- lib/treat/entities/abilities/delegatable.rb
+- lib/treat/entities/abilities/doable.rb
+- lib/treat/entities/abilities/exportable.rb
+- lib/treat/entities/abilities/iterable.rb
+- 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/entity.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/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/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/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/topic_words/lda/data.dat
-- lib/treat/extractors/topic_words/lda/wiki.yml
+- lib/treat/extractors/time/ruby.rb
 - lib/treat/extractors/topic_words/lda.rb
-- lib/treat/extractors/topics/reuters/industry.xml
-- lib/treat/extractors/topics/reuters/region.xml
-- lib/treat/extractors/topics/reuters/topics.xml
 - 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
@@ -218,23 +134,23 @@ files:
 - lib/treat/formatters/unserializers/xml.rb
 - lib/treat/formatters/unserializers/yaml.rb
 - lib/treat/formatters/visualizers/dot.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/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/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/install.rb
+- lib/treat/installer.rb
 - lib/treat/kernel.rb
 - lib/treat/languages/arabic.rb
 - lib/treat/languages/chinese.rb
@@ -250,77 +166,61 @@ files:
 - 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/wordnet.rb
-- lib/treat/lexicalizers/tag/brill.rb
-- lib/treat/lexicalizers/tag/lingua.rb
-- lib/treat/lexicalizers/tag/stanford.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/linguistics/categories.rb
+- lib/treat/linguistics/tags.rb
+- lib/treat/linguistics.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/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
-- lib/treat/processors/tokenizers/macintyre.rb
-- lib/treat/processors/tokenizers/multilingual.rb
 - lib/treat/processors/tokenizers/perl.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/proxies.rb
-- lib/treat/registrable.rb
 - lib/treat/retrievers/indexers/ferret.rb
 - lib/treat/retrievers/searchers/ferret.rb
 - lib/treat/retrievers.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_entity.rb
-- test/tc_extractors.rb
-- test/tc_formatters.rb
-- test/tc_inflectors.rb
-- test/tc_lexicalizers.rb
-- test/tc_processors.rb
-- test/tc_resources.rb
-- test/tc_treat.rb
-- test/tc_tree.rb
-- test/tests.rb
-- test/texts/english/half_cocked_basel.txt
-- test/texts/english/hose_and_dry.doc
-- test/texts/english/hungarys_troubles.abw
-- test/texts/english/long.html
-- test/texts/english/long.txt
-- test/texts/english/medium.txt
-- test/texts/english/republican_nomination.pdf
-- test/texts/english/saving_the_euro.odt
-- test/texts/english/short.txt
-- test/texts/english/zero_sum.html
-- test/texts.rb
+- spec/collection.rb
+- spec/document.rb
+- spec/entity.rb
+- spec/languages.rb
+- spec/phrase.rb
+- spec/samples/mathematicians/archimedes.abw
+- spec/samples/mathematicians/euler.html
+- spec/samples/mathematicians/gauss.pdf
+- spec/samples/mathematicians/leibniz.txt
+- spec/samples/mathematicians/newton.doc
+- spec/sandbox.rb
+- spec/token.rb
+- spec/treat.rb
+- spec/tree.rb
+- spec/word.rb
+- spec/zone.rb
 - tmp/INFO
-- README
-- TODO
+- files/INFO
+- README.md
 - LICENSE
-- INSTALL
 homepage: https://github.com/louismullie/treat
 licenses: []
 post_install_message: 
@@ -341,9 +241,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.15
+rubygems_version: 1.8.21
 signing_key: 
 specification_version: 3
-summary: Text retrieval, extraction and annotation toolkit
+summary: A text retrieval, extraction and annotation toolkit for Ruby.
 test_files: []
-has_rdoc: