engtagger 0.1.2 → 0.2.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 47684458b8965c2c1f52d0d29ca2cad340b0ed3f
+  data.tar.gz: aa6dbd0473409e9b6b2987a42c126a6b10dce096
+SHA512:
+  metadata.gz: cddd67eab940146a2426032714aedd8e5195192ead3133ade5f76c594c5f0667f0747bba8b019f63df91dd2eb0610da19288a9e06a2323eb7bde91fec025b028
+  data.tar.gz: a76ca3422b9a3a1a813263b6e4ab5e69ca74ac998afcc259be55a6441b6b46b21ac9de6eb241327956a6fda1c2d3dbd033ba1678df86506f153089a3ef99d46d

data/README.md

@@ -54,7 +54,16 @@ of regular expressions.
     proper = tgr.get_proper_nouns(tagged)
 
     #=> {"Alice"=>1}
-  
+
+    # Get all past tense verbs
+    pt_verbs = tgr.get_past_tense_verbs(tagged)
+
+    #=> {"chased"=>1}
+
+    # Get all the adjectives
+    adj = tgr.get_adjectives(tagged)
+
+    #=> {"big"=>1, "fat"=>1}
 
     # Get all noun phrases of any syntactic level
     # (same as word_list but take a tagged input)
@@ -126,6 +135,11 @@ of this Ruby library
 
 * Yoichiro Hasebe (yohasebe [at] gmail.com) 
 
+### Contributors
+
+* Carlos Ramirez III
+* Phil London
+
 ### Acknowledgement
 
 This Ruby library is a direct port of Lingua::EN::Tagger available at CPAN.

data/lib/engtagger.rb

@@ -59,7 +59,6 @@ class EngTagger
   NUM   = get_ext('cd')
   GER   = get_ext('vbg')
   ADJ   = get_ext('jj[rs]*')
-  PART  = get_ext('vbn')
   NN    = get_ext('nn[sp]*')
   NNP   = get_ext('nnp')
   PREP  = get_ext('in')
@@ -68,6 +67,15 @@ class EngTagger
   QUOT  = get_ext('ppr')
   SEN   = get_ext('pp')
   WORD  = get_ext('\w+')
+  VB    = get_ext('vb')
+  VBG   = get_ext('vbg')
+  VBD   = get_ext('vbd')
+  PART  = get_ext('vbn')   
+  VBP   = get_ext('vbp')
+  VBZ   = get_ext('vbz')
+  JJ    = get_ext('jj')
+  JJR   = get_ext('jjr')
+  JJS   = get_ext('jjs')
 
   # Convert a Treebank-style, abbreviated tag into verbose definitions 
   def self.explain_tag(tag)
@@ -183,7 +191,7 @@ class EngTagger
     @conf[:debug] = false
     # assuming that we start analyzing from the beginninga new sentence...
     @conf[:current_tag] = 'pp' 
-    @conf.merge(params) if params
+    @conf.merge!(params)
     unless File.exists?(@conf[:word_path]) and File.exists?(@conf[:tag_path])
       print "Couldn't locate POS lexicon, creating a new one" if @conf[:debug]
       @@hmm = Hash.new
@@ -321,7 +329,143 @@ class EngTagger
     end
     return ret
   end
+
+  def get_infinitive_verbs(tagged)
+    return nil unless valid_text(tagged)
+    VB
+    trimmed = tagged.scan(VB).map do |n|
+      strip_tags(n)
+    end
+    ret = Hash.new(0)
+    trimmed.each do |n|
+      n = stem(n)
+      next unless n.length < 100  # sanity check on word length
+      ret[n] += 1 unless n =~ /\A\s*\z/
+    end
+    return ret
+  end
+
+  def get_past_tense_verbs(tagged)
+    return nil unless valid_text(tagged)
+    VBD
+    trimmed = tagged.scan(VBD).map do |n|
+      strip_tags(n)
+    end
+    ret = Hash.new(0)
+    trimmed.each do |n|
+      n = stem(n)
+      next unless n.length < 100  # sanity check on word length
+      ret[n] += 1 unless n =~ /\A\s*\z/
+    end
+    return ret
+  end
+
+  def get_gerund_verbs(tagged)
+    return nil unless valid_text(tagged)
+    VBG
+    trimmed = tagged.scan(VB).map do |n|
+      strip_tags(n)
+    end
+    ret = Hash.new(0)
+    trimmed.each do |n|
+      n = stem(n)
+      next unless n.length < 100  # sanity check on word length
+      ret[n] += 1 unless n =~ /\A\s*\z/
+    end
+    return ret
+  end
+
+  def get_passive_verbs(tagged)
+    return nil unless valid_text(tagged)
+    PART
+    trimmed = tagged.scan(PART).map do |n|
+      strip_tags(n)
+    end
+    ret = Hash.new(0)
+    trimmed.each do |n|
+      n = stem(n)
+      next unless n.length < 100  # sanity check on word length
+      ret[n] += 1 unless n =~ /\A\s*\z/
+    end
+    return ret
+  end
+
   
+  def get_base_present_verbs(tagged)
+    return nil unless valid_text(tagged)
+    VBP
+    trimmed = tagged.scan(VBP).map do |n|
+      strip_tags(n)
+    end
+    ret = Hash.new(0)
+    trimmed.each do |n|
+      n = stem(n)
+      next unless n.length < 100  # sanity check on word length
+      ret[n] += 1 unless n =~ /\A\s*\z/
+    end
+    return ret
+  end
+
+  def get_present_verbs(tagged)
+    return nil unless valid_text(tagged)
+    VBZ
+    trimmed = tagged.scan(VBZ).map do |n|
+      strip_tags(n)
+    end
+    ret = Hash.new(0)
+    trimmed.each do |n|
+      n = stem(n)
+      next unless n.length < 100  # sanity check on word length
+      ret[n] += 1 unless n =~ /\A\s*\z/
+    end
+    return ret
+  end
+
+  def get_adjectives(tagged)
+    return nil unless valid_text(tagged)
+    JJ
+    trimmed = tagged.scan(JJ).map do |n|
+      strip_tags(n)
+    end
+    ret = Hash.new(0)
+    trimmed.each do |n|
+      n = stem(n)
+      next unless n.length < 100  # sanity check on word length
+      ret[n] += 1 unless n =~ /\A\s*\z/
+    end
+    return ret
+  end
+
+  def get_comparative_adjectives(tagged)
+    return nil unless valid_text(tagged)
+    JJR
+    trimmed = tagged.scan(JJR).map do |n|
+      strip_tags(n)
+    end
+    ret = Hash.new(0)
+    trimmed.each do |n|
+      n = stem(n)
+      next unless n.length < 100  # sanity check on word length
+      ret[n] += 1 unless n =~ /\A\s*\z/
+    end
+    return ret
+  end  
+
+  def get_superlative_adjectives(tagged)
+    return nil unless valid_text(tagged)
+    JJS
+    trimmed = tagged.scan(JJS).map do |n|
+      strip_tags(n)
+    end
+    ret = Hash.new(0)
+    trimmed.each do |n|
+      n = stem(n)
+      next unless n.length < 100  # sanity check on word length
+      ret[n] += 1 unless n =~ /\A\s*\z/
+    end
+    return ret
+  end
+
   # Given a POS-tagged text, this method returns only the maximal noun phrases.
   # May be called directly, but is also used by get_noun_phrases
   def get_max_noun_phrases(tagged)

data/lib/engtagger/version.rb

@@ -1,3 +1,3 @@
 module EngTagger
-  VERSION = "0.1.2"
+  VERSION = "0.2.0"
 end

data/test/test_engtagger.rb

@@ -191,6 +191,11 @@ EOD
     text = ""
     assert(!@tagger.valid_text(text))
   end
+  
+  def test_override_default_params
+    @tagger = EngTagger.new(:longest_noun_phrase => 3)
+    assert_equal 3, @tagger.conf[:longest_noun_phrase]
+  end
 end
 
 # Number of errors detected: 24

metadata

@@ -1,15 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: engtagger
 version: !ruby/object:Gem::Version
-  version: 0.1.2
-  prerelease: 
+  version: 0.2.0
 platform: ruby
 authors:
 - Yoichiro Hasebe
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-06-05 00:00:00.000000000 Z
+date: 2014-04-20 00:00:00.000000000 Z
 dependencies: []
 description: A Ruby port of Perl Lingua::EN::Tagger, a probability based, corpus-trained
   tagger that assigns POS tags to English text based on a lookup dictionary and a
@@ -20,7 +19,7 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- .gitignore
+- ".gitignore"
 - Gemfile
 - LICENSE
 - README.md
@@ -37,27 +36,26 @@ files:
 - test/test_engtagger.rb
 homepage: http://github.com/yohasebe/engtagger
 licenses: []
+metadata: {}
 post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.24
+rubygems_version: 2.2.2
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: A probability based, corpus-trained English POS tagger
 test_files:
 - test/test_engtagger.rb