words 0.2.0 → 0.2.1

data/README.markdown

@@ -56,8 +56,12 @@ Then your ready to rock and roll. :)
 To build the wordnet dataset (or index for pure) file yourself, from the original wordnet files, you can use the bundled "build_wordnet" command
 
 	build_wordnet -h # this will give you the usage information
-	sudo build_wordnet -v --build-tokyo # this would attempt to build the tokyo backend data locating the original wordnet files through a search...
-	sudo build_wordnet -v --build-pure # this would attempt to build the pure backend index locating the original wordnet files through a search...
+	
+	# this would attempt to build the tokyo backend data locating the original wordnet files through a search...
+	sudo build_wordnet -v --build-tokyo
+	
+	# this would attempt to build the pure backend index locating the original wordnet files through a search...
+	sudo build_wordnet -v --build-pure
 
 ## Usage ##
 

data/Rakefile

@@ -5,8 +5,8 @@ begin
   require 'jeweler'
   Jeweler::Tasks.new do |gem|
     gem.name = "words"
-    gem.summary = %Q{A fast, easy to use interface to WordNet® with cross ruby distribution compatability.}
-    gem.description = %Q{A fast, easy to use interface to WordNet® with cross ruby distribution compatability. We use TokyoCabinet to store the dataset and the excellent rufus-tokyo to interface with it. This allows us to have full compatability across ruby distributions while still remaining both fast and simple to use.}
+    gem.summary = %Q{A Fast & Easy to use interface to WordNet® with cross ruby distribution compatability.}
+    gem.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!}
     gem.email = "roja@arbia.co.uk"
     gem.homepage = "http://github.com/roja/words"
     gem.authors = ["Roja Buck"]
@@ -14,8 +14,12 @@ begin
     gem.add_dependency 'rufus-tokyo', '>= 1.0.5'
     gem.executables = [ "build_wordnet" ]
     gem.default_executable = "build_wordnet"
+    gem.rubyforge_project = 'words'
   end
   Jeweler::GemcutterTasks.new
+  Jeweler::RubyforgeTasks.new do |rubyforge|
+    rubyforge.doc_task = "rdoc"
+  end
 rescue LoadError
   puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
 end

data/VERSION

@@ -1 +1 @@
-0.2.0
+0.2.1

data/bin/build_wordnet

@@ -19,102 +19,102 @@ def locate_wordnet(base_dir)
   return path + "dict" if (path + "dict/data.noun").exist?
 end
 
-if __FILE__ == $0
-  
-  puts "Words Dataset Constructor 2010 (c) Roja Buck"
-  
-  opts = Trollop::options do
-    opt :verbose, "Output verbose program detail.", :default => false
-    opt :wordnet, "Location of the wordnet dictionary directory", :default => "Search..."
-    opt :build_tokyo, "Build the tokyo dataset?", :default => false
-    opt :build_pure, "Build the pure ruby dataset?", :default => false
-  end
-  Trollop::die :build_tokyo, "Either tokyo dataset or pure ruby dataset are required" if !opts[:build_tokyo] && !opts[:build_pure]
-  puts "Verbose mode enabled" if (VERBOSE = opts[:verbose])
-  
-  wordnet_dir = nil
-  if opts[:wordnet] == "Search..."
-    ['/usr/share/wordnet', '/usr/local/share/wordnet', '/usr/local/WordNet-3.0'].each do |potential_dir|
-      break unless (wordnet_dir = locate_wordnet potential_dir).nil?
-    end
-    abort( "Unable to locate wordnet dictionary. To specify check --help." ) if wordnet_dir.nil?
-  else
-    wordnet_dir = locate_wordnet opts[:wordnet]
-    abort( "Unable to locate wordnet dictionary in directory #{opts[:wordnet]}. Please check and try again." ) if wordnet_dir.nil?
+puts "Words Dataset Constructor 2010 (c) Roja Buck"
+
+opts = Trollop::options do
+  opt :verbose, "Output verbose program detail.", :default => false
+  opt :wordnet, "Location of the wordnet dictionary directory", :default => "Search..."
+  opt :build_tokyo, "Build the tokyo dataset?", :default => false
+  opt :build_pure, "Build the pure ruby dataset?", :default => false
+end
+Trollop::die :build_tokyo, "You need to specify whether tokyo dataset or pure ruby index building is required" if !opts[:build_tokyo] && !opts[:build_pure]
+puts "Verbose mode enabled" if (VERBOSE = opts[:verbose])
+
+gem_path = Pathname.new "#{File.dirname(__FILE__)}/.."
+abort "Ensure you run the command using sudo or as a Superuser / Administrator" unless gem_path.writable?
+data_path = gem_path + "data/"
+data_path.mkpath
+
+wordnet_dir = nil
+if opts[:wordnet] == "Search..."
+  ['/usr/share/wordnet', '/usr/local/share/wordnet', '/usr/local/WordNet-3.0'].each do |potential_dir|
+    break unless (wordnet_dir = locate_wordnet potential_dir).nil?
   end
+  abort( "Unable to locate wordnet dictionary. To specify check --help." ) if wordnet_dir.nil?
+else
+  wordnet_dir = locate_wordnet opts[:wordnet]
+  abort( "Unable to locate wordnet dictionary in directory #{opts[:wordnet]}. Please check and try again." ) if wordnet_dir.nil?
+end
+
+# At this point we know we should have a wordnet directory within wordnet_dir
+puts "Found wordnet files in #{wordnet_dir}..." if VERBOSE
+
+index_files = POS_FILE_TYPES.map { |pos| wordnet_dir + "index.#{pos}" }
+data_files = POS_FILE_TYPES.map { |pos| wordnet_dir + "data.#{pos}" }
+
+ (index_files + data_files).each do |required_file|
+  abort( "Unable to locate #{required_file} within the wordnet dictionary. Please check your wordnet copy is valid and try again." ) unless required_file.exist?
+  abort( "Cannot get readable permissions to #{required_file} within the wordnet dictionary. Please check the file permissions and try again." ) unless required_file.readable?
+end
+
+# At this point we know we have the correct files, though we don't know there validity
+puts "Validated existance of wordnet files in #{wordnet_dir}..." if VERBOSE
+
+# Build data
+
+index_hash = Hash.new
+data_hash = Hash.new
+POS_FILE_TYPES.each do |file_pos|
   
-  # At this point we know we should have a wordnet directory within wordnet_dir
-  puts "Found wordnet files in #{wordnet_dir}..." if VERBOSE
-  
-  index_files = POS_FILE_TYPES.map { |pos| wordnet_dir + "index.#{pos}" }
-  data_files = POS_FILE_TYPES.map { |pos| wordnet_dir + "data.#{pos}" }
+  puts "Building #{file_pos} indexes..." if VERBOSE
   
-   (index_files + data_files).each do |required_file|
-    abort( "Unable to locate #{required_file} within the wordnet dictionary. Please check your wordnet copy is valid and try again." ) unless required_file.exist?
-    abort( "Cannot get readable permissions to #{required_file} within the wordnet dictionary. Please check the file permissions and try again." ) unless required_file.readable?
+  # add indexes
+   (wordnet_dir + "index.#{file_pos}").each_line do |index_line|
+    next if index_line[0, 2] == "  "
+    index_parts = index_line.split(" ")
+    
+    lemma, pos, synset_count, pointer_count = index_parts.shift, index_parts.shift, index_parts.shift.to_i, index_parts.shift.to_i
+    pointer_symbols = Array.new(pointer_count).map { POS_FILE_TYPE_TO_SHORT[file_pos] + index_parts.shift }
+    sense_count = index_parts.shift
+    tagsense_count = pos + index_parts.shift
+    synset_ids = Array.new(synset_count).map { POS_FILE_TYPE_TO_SHORT[file_pos] + index_parts.shift }
+    
+    index_hash[lemma] = { "synset_ids" => [], "tagsense_counts" => [] } if index_hash[lemma].nil?
+    index_hash[lemma] = { "lemma" => lemma, "synset_ids" => index_hash[lemma]["synset_ids"] + synset_ids, "tagsense_counts" => index_hash[lemma]["tagsense_counts"] + [tagsense_count] }
+    
   end
   
-  # At this point we know we have the correct files, though we don't know there validity
-  puts "Validated existance of wordnet files in #{wordnet_dir}..." if VERBOSE
-  
-  # Build data
-  
-  index_hash = Hash.new
-  data_hash = Hash.new
-  POS_FILE_TYPES.each do |file_pos|
-    
-    puts "Building #{file_pos} indexes..." if VERBOSE
+  if opts[:build_tokyo]
+    puts "Building #{file_pos} data..." if VERBOSE
     
-    # add indexes
-     (wordnet_dir + "index.#{file_pos}").each_line do |index_line|
-      next if index_line[0, 2] == "  "
-      index_parts = index_line.split(" ")
-      
-      lemma, pos, synset_count, pointer_count = index_parts.shift, index_parts.shift, index_parts.shift.to_i, index_parts.shift.to_i
-      pointer_symbols = Array.new(pointer_count).map { POS_FILE_TYPE_TO_SHORT[file_pos] + index_parts.shift }
-      sense_count = index_parts.shift
-      tagsense_count = pos + index_parts.shift
-      synset_ids = Array.new(synset_count).map { POS_FILE_TYPE_TO_SHORT[file_pos] + index_parts.shift }
+    # add data
+     (wordnet_dir + "data.#{file_pos}").each_line do |data_line|
+      next if data_line[0, 2] == "  "
+      data_line, gloss = data_line.split(" | ")
+      data_parts = data_line.split(" ")
       
-      index_hash[lemma] = { "synset_ids" => [], "tagsense_counts" => [] } if index_hash[lemma].nil?
-      index_hash[lemma] = { "lemma" => lemma, "synset_ids" => index_hash[lemma]["synset_ids"] + synset_ids, "tagsense_counts" => index_hash[lemma]["tagsense_counts"] + [tagsense_count] }
+      synset_id, lexical_filenum, synset_type, word_count = POS_FILE_TYPE_TO_SHORT[file_pos] + data_parts.shift, data_parts.shift, data_parts.shift, data_parts.shift.to_i(16)
+      words = Array.new(word_count).map { "#{data_parts.shift}.#{data_parts.shift}" }
+      relations = Array.new(data_parts.shift.to_i).map { "#{data_parts.shift}.#{data_parts.shift}.#{data_parts.shift}.#{data_parts.shift}" }
       
-    end
-    
-    if opts[:build_tokyo]
-      puts "Building #{file_pos} data..." if VERBOSE
-      
-      # add data
-       (wordnet_dir + "data.#{file_pos}").each_line do |data_line|
-        next if data_line[0, 2] == "  "
-        data_line, gloss = data_line.split(" | ")
-        data_parts = data_line.split(" ")
-        
-        synset_id, lexical_filenum, synset_type, word_count = POS_FILE_TYPE_TO_SHORT[file_pos] + data_parts.shift, data_parts.shift, data_parts.shift, data_parts.shift.to_i(16)
-        words = Array.new(word_count).map { "#{data_parts.shift}.#{data_parts.shift}" }
-        relations = Array.new(data_parts.shift.to_i).map { "#{data_parts.shift}.#{data_parts.shift}.#{data_parts.shift}.#{data_parts.shift}" }
-        
-        data_hash[synset_id] = { "synset_id" => synset_id, "lexical_filenum" => lexical_filenum, "synset_type" => synset_type, 
+      data_hash[synset_id] = { "synset_id" => synset_id, "lexical_filenum" => lexical_filenum, "synset_type" => synset_type, 
                           "words" => words.join('|'), "relations" => relations.join('|'), "gloss" => gloss.strip }
-      end
     end
-    
-  end
-  
-  if opts[:build_tokyo]
-    tokyo_hash = Rufus::Tokyo::Table.new("#{File.dirname(__FILE__)}/../data/wordnet.tct")
-    index_hash.each { |k,v| tokyo_hash[k] = { "lemma" => v["lemma"], "synset_ids" => v["synset_ids"].join('|'), "tagsense_counts" => v["tagsense_counts"].join('|') } }
-    data_hash.each { |k,v| tokyo_hash[k] = v }
-    tokyo_hash.close
   end
   
-  if opts[:build_pure]
-    index = Hash.new
-    index_hash.each { |k,v| index[k] = [v["lemma"], v["tagsense_counts"].join('|'), v["synset_ids"].join('|')] }
-    File.open("#{File.dirname(__FILE__)}/../data/index.dmp",'w') do |file|
-      file.write Marshal.dump(index)
-    end
+end
+
+if opts[:build_tokyo]
+  tokyo_hash = Rufus::Tokyo::Table.new((data_path + "wordnet.tct").to_s)
+  index_hash.each { |k,v| tokyo_hash[k] = { "lemma" => v["lemma"], "synset_ids" => v["synset_ids"].join('|'), "tagsense_counts" => v["tagsense_counts"].join('|') } }
+  data_hash.each { |k,v| tokyo_hash[k] = v }
+  tokyo_hash.close
+end
+
+if opts[:build_pure]
+  index = Hash.new
+  index_hash.each { |k,v| index[k] = [v["lemma"], v["tagsense_counts"].join('|'), v["synset_ids"].join('|')] }
+  File.open(data_path + "index.dmp",'w') do |file|
+    file.write Marshal.dump(index)
   end
-  
-  
-end
+end

data/examples.rb

@@ -1,10 +1,11 @@
 #!/usr/bin/env ruby
 
-require 'lib/words'
+require 'rubygems'
+require 'words'
 
 if __FILE__ == $0
   
-  wordnet = Words::Words.new  # :pure
+  wordnet = Words::Words.new  :pure
   
   puts wordnet
   

data/lib/words.rb

@@ -21,7 +21,7 @@ module Words
       
       if @data_path.exist?
         if @connection_type == :tokyo
-          @connection = Rufus::Tokyo::Table.new(@data_path.to_s)
+          @connection = Rufus::Tokyo::Table.new(@data_path.to_s, :mode => 'r')
           @connected = true
         elsif @connection_type == :pure
           # open the index is there

data/words.gemspec

@@ -5,13 +5,13 @@
 
 Gem::Specification.new do |s|
   s.name = %q{words}
-  s.version = "0.2.0"
+  s.version = "0.2.1"
 
   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.default_executable = %q{build_wordnet}
-  s.description = %q{A fast, easy to use interface to WordNet® with cross ruby distribution compatability. We use TokyoCabinet to store the dataset and the excellent rufus-tokyo to interface with it. This allows us to have full compatability across ruby distributions while still remaining both fast and simple to use.}
+  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}
   s.executables = ["build_wordnet"]
   s.extra_rdoc_files = [
@@ -34,8 +34,9 @@ Gem::Specification.new do |s|
   s.homepage = %q{http://github.com/roja/words}
   s.rdoc_options = ["--charset=UTF-8"]
   s.require_paths = ["lib"]
+  s.rubyforge_project = %q{words}
   s.rubygems_version = %q{1.3.5}
-  s.summary = %q{A fast, easy to use interface to WordNet® with cross ruby distribution compatability.}
+  s.summary = %q{A Fast & Easy to use interface to WordNet® with cross ruby distribution compatability.}
   s.test_files = [
     "test/test_words.rb",
      "test/helper.rb"

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: words
 version: !ruby/object:Gem::Version 
-  version: 0.2.0
+  version: 0.2.1
 platform: ruby
 authors: 
 - Roja Buck
@@ -32,7 +32,7 @@ dependencies:
       - !ruby/object:Gem::Version 
         version: 1.0.5
     version: 
-description: "A fast, easy to use interface to WordNet\xC2\xAE with cross ruby distribution compatability. We use TokyoCabinet to store the dataset and the excellent rufus-tokyo to interface with it. This allows us to have full compatability across ruby distributions while still remaining both fast and simple to use."
+description: "Words, with both pure ruby & tokyo-cabinate backends, implements a fast interface to Wordnet\xC2\xAE 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\xC2\xAE. I have attempted to provide ease of use in the form of a simple yet powerful api and installation is a sintch!"
 email: roja@arbia.co.uk
 executables: 
 - build_wordnet
@@ -76,11 +76,11 @@ required_rubygems_version: !ruby/object:Gem::Requirement
   version: 
 requirements: []
 
-rubyforge_project: 
+rubyforge_project: words
 rubygems_version: 1.3.5
 signing_key: 
 specification_version: 3
-summary: "A fast, easy to use interface to WordNet\xC2\xAE with cross ruby distribution compatability."
+summary: "A Fast & Easy to use interface to WordNet\xC2\xAE with cross ruby distribution compatability."
 test_files: 
 - test/test_words.rb
 - test/helper.rb