words 0.2.1 → 0.2.2

data/VERSION

@@ -1 +1 @@
-0.2.1
+0.2.2

data/lib/words.rb

@@ -40,7 +40,7 @@ module Words
         end
       else
         @connected = false
-        raise "Failed to locate the words #{ @connection_type == :pure ? 'index' : 'dataset' } at #{@data_path}. Please insure you have created it using the words gems provided 'build_dataset.rb' command."
+        raise "Failed to locate the words #{ @connection_type == :pure ? 'index' : 'dataset' } at #{@data_path}. Please insure you have created it using the words gems provided 'build_wordnet' command."
       end
       
     end
@@ -53,10 +53,10 @@ module Words
       return true
     end
     
-    def lemma(term)
+    def homographs(term)
       if connection_type == :pure
-        raw_lemma = @connection[term]
-        { 'lemma' => raw_lemma[0], 'tagsense_counts' => raw_lemma[1], 'synset_ids' => raw_lemma[2]}
+        raw_homographs = @connection[term]
+        { 'lemma' => raw_homographs[0], 'tagsense_counts' => raw_homographs[1], 'synset_ids' => raw_homographs[2]}
       else
         @connection[term]
       end
@@ -168,6 +168,7 @@ module Words
   class Synset
     
     SYNSET_TYPE_TO_SYMBOL = {"n" => :noun, "v" => :verb, "a" => :adjective, "r" => :adverb, "s" => :adjective_satallite }
+    SYNSET_TYPE_TO_NUMBER = { "n" => 1, "v" => 2, "a" => 3, "r" => 4, "s" => 5 }
     NUM_TO_LEX = [ { :lex => :adj_all, :description => "all adjective clusters" },
     { :lex => :adj_pert, :description => "relational adjectives (pertainyms)" },
     { :lex => :adv_all, :description => "all adverbs" },
@@ -214,9 +215,10 @@ module Words
     { :lex => :verb_weather, :description => "verbs of raining, snowing, thawing, thundering" },
     { :lex => :adj_ppl, :description => "participial adjectives" } ]
     
-    def initialize(synset_id, wordnet_connection)
+    def initialize(synset_id, wordnet_connection, homographs)
       @wordnet_connection = wordnet_connection
       @synset_hash = wordnet_connection.synset(synset_id)
+      @homographs = homographs
       # construct some conveniance menthods for relation type access
       Relation::SYMBOL_TO_RELATION.keys.each do |relation_type|
         self.class.send(:define_method, "#{relation_type}s?") do 
@@ -237,17 +239,22 @@ module Words
       @words
     end
     
+    def lexical_ids
+      @words = words_with_num.map { |word_with_num| word_with_num[:lexical_id] } unless defined? @words
+      @words
+    end
+    
     def size
       words.size
     end
     
-    def words_with_num
-      @words_with_num = @synset_hash["words"].split('|').map { |word| word_parts = word.split('.'); { :word => word_parts[0].gsub('_', ' '), :num => word_parts[1] } } unless defined? @words_with_num
+    def words_with_lexical_ids
+      @words_with_num = @synset_hash["words"].split('|').map { |word| word_parts = word.split('.'); { :word => word_parts[0].gsub('_', ' '), :lexical_id => word_parts[1] } } unless defined? @words_with_num
       @words_with_num
     end
     
     def lexical_filenum
-      @synset_hash["lexical_filenum"].to_i
+      @synset_hash["lexical_filenum"]
     end
     
     def lexical_catagory
@@ -259,7 +266,7 @@ module Words
     end
     
     def lexical
-      NUM_TO_LEX[@synset_hash["lexical_filenum"].to_i]
+      NUM_TO_LEX[lexical_filenum.to_i]
     end
     
     def synset_id
@@ -270,6 +277,14 @@ module Words
       @synset_hash["gloss"]
     end
     
+    def lemma
+      @homographs.lemma
+    end
+    
+    def homographs
+      @homographs
+    end
+    
     def inspect
       @synset_hash.inspect
     end
@@ -293,22 +308,25 @@ module Words
     
   end
   
-  class Lemma
+  class Homographs
     
     POS_TO_SYMBOL = {"n" => :noun, "v" => :verb, "a" => :adjective, "r" => :adverb}
     SYMBOL_TO_POS = POS_TO_SYMBOL.invert
     
-    def initialize(raw_lemma, wordnet_connection)
+    def initialize(raw_homographs, wordnet_connection)
       @wordnet_connection = wordnet_connection
-      @lemma_hash = raw_lemma
+      @lemma_hash = raw_homographs
       # construct some conveniance menthods for relation type access
       SYMBOL_TO_POS.keys.each do |pos|
         self.class.send(:define_method, "#{pos}s?") do 
-          synsets(pos).size > 0
+          size(pos) > 0
         end
         self.class.send(:define_method, "#{pos}s") do 
           synsets(pos)
         end
+        self.class.send(:define_method, "#{pos}_count") do 
+          size(pos)
+        end
         self.class.send(:define_method, "#{pos}_ids") do 
           synset_ids(pos)
         end
@@ -316,12 +334,12 @@ module Words
     end
     
     def tagsense_counts
-      @tagsense_counts = @lemma_hash["tagsense_counts"].split('|').map { |count| { POS_TO_SYMBOL[count[0,1]] => count[1..-1].to_i }  } unless defined? @tagsense_counts
+      @tagsense_counts = @raw_homographs["tagsense_counts"].split('|').map { |count| { POS_TO_SYMBOL[count[0,1]] => count[1..-1].to_i }  } unless defined? @tagsense_counts
       @tagsense_counts
     end
     
     def lemma
-      @lemma = @lemma_hash["lemma"].gsub('_', ' ') unless defined? @lemma
+      @lemma = @raw_homographs["lemma"].gsub('_', ' ') unless defined? @lemma
       @lemma
     end
     
@@ -335,12 +353,16 @@ module Words
       @to_s
     end
     
+    def size(pos = :all)
+      synset_ids(pos).size
+    end
+    
     def synsets(pos = :all)
-      synset_ids(pos).map { |synset_id| Synset.new synset_id, @wordnet_connection }
+      synset_ids(pos).map { |synset_id| Synset.new synset_id, self, @wordnet_connection }
     end
     
     def synset_ids(pos = :all)
-      @synset_ids = @lemma_hash["synset_ids"].split('|') unless defined? @synset_ids
+      @synset_ids = @raw_homographs["synset_ids"].split('|') unless defined? @synset_ids
       case 
         when SYMBOL_TO_POS.include?(pos.to_sym)
         @synset_ids.select { |synset_id| synset_id[0,1] == SYMBOL_TO_POS[pos.to_sym] }
@@ -352,11 +374,13 @@ module Words
     end
     
     def inspect
-      @lemma_hash.inspect
+      @raw_homographs.inspect
     end
     
     alias word lemma
     alias pos available_pos
+    alias senses synsets
+    alias sense_ids synset_ids
     
   end
   
@@ -369,7 +393,7 @@ module Words
     end
     
     def find(word)
-      Lemma.new  @wordnet_connection.lemma(word), @wordnet_connection
+      Homographs.new  @wordnet_connection.homographs(word), @wordnet_connection
     end
     
     def connection_type

data/words.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{words}
-  s.version = "0.2.1"
+  s.version = "0.2.2"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Roja Buck"]
-  s.date = %q{2010-01-16}
+  s.date = %q{2010-01-17}
   s.default_executable = %q{build_wordnet}
   s.description = %q{Words, with both pure ruby & tokyo-cabinate backends, implements a fast interface to Wordnet® over the same easy-to-use API. The FFI backend makes use of Tokyo Cabinet and the FFI interface, rufus-tokyo, to provide cross ruby distribution compatability and blistering speed. The pure ruby interface operates on a special ruby optimised index along with the basic dictionary files provided by WordNet®. I have attempted to provide ease of use in the form of a simple yet powerful api and installation is a sintch!}
   s.email = %q{roja@arbia.co.uk}

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: words
 version: !ruby/object:Gem::Version 
-  version: 0.2.1
+  version: 0.2.2
 platform: ruby
 authors: 
 - Roja Buck
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-01-16 00:00:00 +00:00
+date: 2010-01-17 00:00:00 +00:00
 default_executable: build_wordnet
 dependencies: 
 - !ruby/object:Gem::Dependency