linguistics 2.0.2 → 2.0.3

data/History.rdoc

@@ -1,3 +1,12 @@
+== v2.0.3 [2013-12-02] Michael Granger <ged@FaerieMUD.org>
+
+A bunch of fixes from Ippei UKAI <ippei_ukai@mac.com>
+
+- fix past tense for words end with y
+- fix past tense for doubling verbs
+- fix present participle conjugation of verbs that end with 'e'
+
+
 == v2.0.2 [2013-02-27] Michael Granger <ged@FaerieMUD.org>
 
 - Fix for Ruby 2: don't memoize the inflector.

data/Manifest.txt

@@ -1,3 +1,4 @@
+.simplecov
 ChangeLog
 History.rdoc
 LICENSE
@@ -24,8 +25,8 @@ lib/linguistics/inflector.rb
 lib/linguistics/iso639.rb
 lib/linguistics/languagebehavior.rb
 lib/linguistics/monkeypatches.rb
-spec/lib/constants.rb
-spec/lib/helpers.rb
+spec/constants.rb
+spec/helpers.rb
 spec/linguistics/en/articles_spec.rb
 spec/linguistics/en/conjugation_spec.rb
 spec/linguistics/en/conjunctions_spec.rb

data/README.rdoc

@@ -75,7 +75,7 @@ the top-level namespace for all your linguistic functions, and then
 register it as being available, like so:
 
     module Linguistics::TLH
-    
+
         # Add Klingon to the list of default languages
         Linguistics.register_language( :tlh, self )
 
@@ -101,13 +101,13 @@ behavior to your spec:
 
     require 'rspec'
     require 'linguistics/languagebehavior'
-    
+
     describe Linguistics::TLH do
-    
+
       it_should_behave_like "a Linguistics language module"
-    
+
       # ... any other specs for your module
-    
+
     end
 
 If you wish to use the logging subsystem set up by Linguistics, you can

data/Rakefile

@@ -1,40 +1,58 @@
 #!/usr/bin/env rake
 
-require 'hoe'
+begin
+	require 'rspec'
+	require 'rspec/core/rake_task'
+rescue LoadError
+	abort "This Rakefile requires RSpec. Try again after doing 'gem install rspec'"
+end
+
+begin
+	require 'hoe'
+rescue LoadError
+	abort "This Rakefile requires Hoe. Try again after doing 'gem install hoe'"
+end
+
+# The path to the generated .gemspec file
+GEMSPEC = '.gemspec'
 
 Hoe.plugin :mercurial
+Hoe.plugin :bundler
+Hoe.plugin :publish
 Hoe.plugin :signing
 
 Hoe.plugins.delete :rubyforge
 
-hoespec = Hoe.spec 'linguistics' do
-	self.name = 'linguistics'
-	self.readme_file = 'README.rdoc'
-	self.history_file = 'History.rdoc'
-	self.extra_rdoc_files = FileList[ '*.rdoc' ]
+hoespec = Hoe.spec 'linguistics' do |spec|
+	spec.name = 'linguistics'
+	spec.readme_file = 'README.rdoc'
+	spec.history_file = 'History.rdoc'
+	spec.extra_rdoc_files = FileList[ '*.rdoc' ]
+	spec.license 'BSD'
 
-	self.developer 'Michael Granger', 'ged@FaerieMUD.org'
+	spec.developer 'Michael Granger', 'ged@FaerieMUD.org'
 
-	self.dependency 'loggability', '~> 0.5'
+	spec.dependency 'loggability', '~> 0.7'
 
-	self.dependency 'hoe-deveiate', '~> 0.1', :development
-	self.dependency 'linkparser', '~> 1.1', :development
-	self.dependency 'wordnet', '~> 0.99', :development
-	self.dependency 'ruby-stemmer', '~> 0.9', :development
+	spec.dependency 'hoe-deveiate', '~> 0.3', :development
+	spec.dependency 'hoe-bundler', '~> 1.2', :development
+	spec.dependency 'linkparser', '~> 1.1', :development
+	spec.dependency 'wordnet', '~> 1.0', :development
+	spec.dependency 'wordnet-defaultdb', '~> 1.0', :development
+	spec.dependency 'ruby-stemmer', '~> 0.9', :development
 
-	self.spec_extras[:licenses] = ["BSD"]
-	self.spec_extras[:rdoc_options] = ['-f', 'fivefish', '-t', 'Ruby Linguistics Toolkit']
-	self.spec_extras[:post_install_message] = [
+	spec.spec_extras[:rdoc_options] = ['-f', 'fivefish', '-t', 'Ruby Linguistics Toolkit']
+	spec.spec_extras[:post_install_message] = [
 			"This library also presents tie-ins for the 'linkparser' and",
 			"'wordnet' libraries, which you can enable by installing the",
 			"gems of the same name."
 		  ].join( "\n" )
 
-	self.require_ruby_version( '>=1.9.3' )
-	self.hg_sign_tags = true if self.respond_to?( :hg_sign_tags= )
-	self.check_history_on_release = true if self.respond_to?( :check_history_on_release= )
+	spec.require_ruby_version( '>=1.9.3' )
+	spec.hg_sign_tags = true if spec.respond_to?( :hg_sign_tags= )
+	spec.check_history_on_release = true if spec.respond_to?( :check_history_on_release= )
 
-	self.rdoc_locations << "deveiate:/usr/local/www/public/code/#{remote_rdoc_dir}"
+	spec.rdoc_locations << "deveiate:/usr/local/www/public/code/#{remote_rdoc_dir}"
 end
 
 ENV['VERSION'] ||= hoespec.spec.version.to_s
@@ -46,3 +64,15 @@ task :coverage do
 	ENV["COVERAGE"] = 'yes'
 	Rake::Task[:spec].invoke
 end
+
+
+desc "generate a gemspec from your Hoe.spec"
+file GEMSPEC => 'Rakefile' do |task|
+	spec = hoespec.spec.dup
+	spec.files.delete( '.gemtest' )
+	spec.version = "#{spec.version}.pre.#{Time.now.strftime("%Y%m%d%H%M%S")}"
+	File.open( task.name, 'w' ) do |fh|
+		fh.write( spec.to_ruby )
+	end
+end
+

data/examples/generalize_sentence.rb

@@ -2,7 +2,7 @@
 
 BEGIN {
 	require 'pathname'
-	
+
 	basedir = Pathname.new( __FILE__ ).dirname.parent.expand_path
 	libdir = basedir + "lib"
 	$LOAD_PATH.unshift( basedir.to_s ) unless $LOAD_PATH.include?( basedir.to_s )
@@ -35,7 +35,7 @@ while input = Readline.readline( "Sentence to generalize: " )
 	subj = sent.subject
 	obj = sent.object
 	verb = sent.verb
-	
+
 	input.sub!( /\b#{subj}\b/, generalized_word(subj) ) if subj
 	input.sub!( /\b#{obj}\b/, generalized_word(obj) ) if obj
 	input.sub!( /\b#{verb}\b/, generalized_word(verb) ) if verb

data/lib/linguistics.rb

@@ -12,10 +12,10 @@ module Linguistics
 
 
 	# Release version
-	VERSION = '2.0.2'
+	VERSION = '2.0.3'
 
 	# VCS version
-	REVISION = %q$Revision: d2eeec0b7832 $
+	REVISION = %q$Revision: ca93740ec59c $
 
 	# The list of Classes to add linguistic behaviours to.
 	DEFAULT_EXT_CLASSES = [ String, Numeric, Array ]
@@ -55,7 +55,7 @@ module Linguistics
 	end
 
 
-	### Register a module as providing linguistic functions for the specified +language+ (a two- 
+	### Register a module as providing linguistic functions for the specified +language+ (a two-
 	### or three-letter ISO639-2 language codes as a Symbol)
 	def self::register_language( language, mod )
 		language_entry = LANGUAGE_CODES[ language.to_sym ] or
@@ -143,7 +143,7 @@ module Linguistics
 		config = languages.pop if languages.last.is_a?( Hash )
 		config ||= {}
 
-		classes = Array(config[:classes]) if config[:classes] 
+		classes = Array(config[:classes]) if config[:classes]
 		classes ||= DEFAULT_EXT_CLASSES
 
 		self.log.debug "Extending %d classes with %d language modules." %

data/lib/linguistics/en/articles.rb

@@ -102,7 +102,7 @@ module Linguistics::EN::Articles
 
 
 	### Return the inflected phrase with the appropriate indefinite article ("a" or
-	### "an") prepended. 
+	### "an") prepended.
 	def a( count=nil )
 		count ||= 1
 		phrase = self.to_s

data/lib/linguistics/en/conjugation.rb

@@ -7,7 +7,7 @@ require 'linguistics/en' unless defined?( Linguistics::EN )
 #
 # == Version
 #
-#  $Id: conjugation.rb,v 8b1c8ec50991 2012/08/22 02:09:29 ged $
+#  $Id: conjugation.rb,v de381a81754d 2013/12/02 18:09:29 ged $
 #
 # == Authors
 #
@@ -147,11 +147,11 @@ module Linguistics::EN::Conjugation
 	def conjugate_present_participle( verb )
 		case verb
 		when /[^aeiou]e$/
-			return verb[ 0..-2 ]
+			return verb[ 0..-2 ] + 'ing'
 		when /ie$/
-			return verb[ 0..-3 ] + 'y'
+			return verb[ 0..-3 ] + 'y' + 'ing'
 		when /[aou]e$/
-			return verb[ 0..-2 ]
+			return verb[ 0..-2 ] + 'ing'
 		else
 			if DOUBLING_VERBS.include?( verb )
 				return verb + verb[ -1 ] + 'ing'
@@ -169,10 +169,10 @@ module Linguistics::EN::Conjugation
 		when /e$/
 			return verb + 'd'
 		when /[^aeiou]y$/
-			return verb[ 0..-1 ] + 'ied'
+			return verb[ 0..-2 ] + 'ied'
 		else
 			if DOUBLING_VERBS.include?( verb )
-				verb = verb[ -2..-1 ] + 'ed'
+				verb = verb + verb[ -1 ] + 'ed'
 			else
 				return verb + 'ed'
 			end

data/lib/linguistics/en/conjunctions.rb

@@ -34,7 +34,7 @@ module Linguistics::EN::Conjunctions
 	### particular element to be omitted from the resulting conjunction. The
 	### following options can be used to control the makeup of the returned
 	### conjunction String:
-	### 
+	###
 	### [<b>:separator</b>]
 	###   Specify one or more characters to separate items in the resulting
 	###   list. Defaults to <tt>', '</tt>.

data/lib/linguistics/en/infinitives.rb

@@ -1061,7 +1061,7 @@ module Linguistics::EN::Infinitives
 			if (( suffix = ((INF_SUFFIX_RULE_ORDER & prefixes.keys).first) ))
 				rule = INF_SUFFIX_RULES[ suffix ][:rule]
 				shortestPrefix = INF_SUFFIX_RULES[ suffix ][:word1]
-				self.log.debug "Using rule %p (%p) for suffix %p" % 
+				self.log.debug "Using rule %p (%p) for suffix %p" %
 					[ rule, shortestPrefix, suffix ] if $DEBUG
 
 				case shortestPrefix

data/lib/linguistics/en/linkparser.rb

@@ -8,35 +8,35 @@ require 'linguistics/en' unless defined?( Linguistics::EN )
 #   # Test to see whether or not the link parser is loaded.
 #   Linguistics::EN.has_link_parser?
 #   # => true
-# 
+#
 #   # Diagram the first linkage for a test sentence
 #   puts "he is a big dog".en.sentence.linkages.first.to_s
-# 	  +---O*---+ 
-# 	  | +--Ds--+ 
-#    +Ss+ |  +-A-+ 
-#    |  | |  |   | 
+#     +---O*---+
+#     | +--Ds--+
+#    +Ss+ |  +-A-+
+#    |  | |  |   |
 #   he is a big dog
-# 
+#
 #   # Find the verb in the sentence
-#   "he is a big dog".en.sentence.verb.to_s      
+#   "he is a big dog".en.sentence.verb.to_s
 #   # => "is"
-# 
+#
 #   # Combined infinitive + LinkParser: Find the infinitive form of the verb of the
 #   given sentence.
 #   "he is a big dog".en.sentence.verb.infinitive
 #   # => "be"
-# 
+#
 #   # Find the direct object of the sentence
 #   "he is a big dog".en.sentence.object.to_s
 #   # => "dog"
-# 
+#
 #   # Combine WordNet + LinkParser to find the definition of the direct object of
 #   # the sentence
 #   "he is a big dog".en.sentence.object.gloss
 #   # => "a member of the genus Canis (probably descended from the common wolf) that
 #   has been domesticated by man since prehistoric times; occurs in many breeds;
 #   \"the dog barked all night\""
-# 
+#
 module Linguistics::EN::LinkParser
 
 	@has_linkparser = false

data/lib/linguistics/en/numbers.rb

@@ -100,7 +100,7 @@ module Linguistics::EN::Numbers
 
 		# Triple-digits
 		proc {|zero,x,y,z|
-			NUMBER_TO_WORDS_FUNCTIONS[1].call(zero,x) + 
+			NUMBER_TO_WORDS_FUNCTIONS[1].call(zero,x) +
 			NUMBER_TO_WORDS_FUNCTIONS[2].call(zero,y,z)
 		}
 	]
@@ -108,24 +108,24 @@ module Linguistics::EN::Numbers
 
 	### Return the specified number as english words. One or more configuration
 	### values may be passed to control the returned String:
-	### 
+	###
 	### [<b>:group</b>]
 	###   Controls how many numbers at a time are grouped together. Valid values
-	###   are <code>0</code> (normal grouping), <code>1</code> (single-digit 
-	###   grouping, e.g., "one, two, three, four"), <code>2</code> 
+	###   are <code>0</code> (normal grouping), <code>1</code> (single-digit
+	###   grouping, e.g., "one, two, three, four"), <code>2</code>
 	###   (double-digit grouping, e.g., "twelve, thirty-four", or <code>3</code>
 	###   (triple-digit grouping, e.g., "one twenty-three, four").
 	### [<b>:comma</b>]
-	###   Set the character/s used to separate word groups. Defaults to 
+	###   Set the character/s used to separate word groups. Defaults to
 	###   <code>", "</code>.
 	### [<b>:and</b>]
-	###   Set the word and/or characters used where <code>' and ' </code>(the 
-	###   default) is normally used. Setting <code>:and</code> to 
-	###   <code>' '</code>, for example, will cause <code>2556</code> to be 
-	###   returned as "two-thousand, five hundred fifty-six" instead of 
+	###   Set the word and/or characters used where <code>' and ' </code>(the
+	###   default) is normally used. Setting <code>:and</code> to
+	###   <code>' '</code>, for example, will cause <code>2556</code> to be
+	###   returned as "two-thousand, five hundred fifty-six" instead of
 	###   "two-thousand, five hundred and fifty-six".
 	### [<b>:zero</b>]
-	###   Set the word used to represent the numeral <code>0</code> in the 
+	###   Set the word used to represent the numeral <code>0</code> in the
 	###   result. <code>'zero'</code> is the default.
 	### [<b>:decimal</b>]
 	###   Set the translation of any decimal points in the number; the default
@@ -288,7 +288,7 @@ module Linguistics::EN::Numbers
 
 
 	### Return a phrase describing the specified +number+ of objects in the
-	### inflected object in general terms. The following options can be used to 
+	### inflected object in general terms. The following options can be used to
 	### control the makeup of the returned quantity String:
 	###
     ### [<b>:joinword</b>]

data/lib/linguistics/en/participles.rb

@@ -10,7 +10,7 @@ module Linguistics::EN::Participles
 	Linguistics::EN.register_extension( self )
 
 
-	### Attempt to return the inflected string in its present participle 
+	### Attempt to return the inflected string in its present participle
 	### form (e.g., talked -> talking).
 	def present_participle
         plural = self.to_s.en.plural_verb

data/lib/linguistics/en/pluralization.rb

@@ -3,7 +3,7 @@
 require 'linguistics/en' unless defined?( Linguistics )
 
 # Plural inflection methods for the English-language Linguistics module.
-# 
+#
 # It provides conversion of plural forms of all nouns, most verbs,
 # and some adjectives. It also provides "classical" variants (for
 # example: "brother" -> "brethren", "dogma" -> "dogmata", etc.) where
@@ -92,13 +92,13 @@ module Linguistics::EN::Pluralization
 
 	# Classical "..um" -> "..a"
 	PL_sb_C_um_a = matchgroup %w[
-		maximum	minimum	momentum	optimum
-		quantum	cranium	curriculum	dictum
-		phylum	aquarium	compendium	emporium
-		enconium	gymnasium	honorarium	interregnum
-		lustrum 	memorandum	millenium 	rostrum 
-		spectrum	speculum	stadium	trapezium
-		ultimatum	medium	vacuum	velum 
+		maximum minimum momentum optimum
+		quantum cranium curriculum dictum
+		phylum aquarium compendium emporium
+		enconium gymnasium honorarium interregnum
+		lustrum memorandum millenium  rostrum
+		spectrum speculum stadium trapezium
+		ultimatum medium vacuum velum
 		consortium
 	].collect {|word| word[0...-2]}
 
@@ -150,7 +150,7 @@ module Linguistics::EN::Pluralization
 		ghetto	guano	inferno
 		jumbo	lumbago	magneto
 		manifesto	medico	octavo
-		photo	pro		quarto	
+		photo	pro		quarto
 		canto	lingo	generalissimo
 		stylo	rhino
 	] | PL_sb_C_o_i_a )
@@ -259,7 +259,7 @@ module Linguistics::EN::Pluralization
 			epidermis ethos eyas gas glottis hepatitis
 			hubris ibis lens mantis marquis metropolis
 			neuritis pathos pelvis polis rhinoceros
-			sassafras tonsillitis trellis 
+			sassafras tonsillitis trellis
 		]
 
 	PL_v_special_s = matchgroup [
@@ -327,7 +327,7 @@ module Linguistics::EN::Pluralization
 
 	PL_v_irregular_pres_h = {
 		#	1St pers. sing.		2nd pers. sing.		3rd pers. singular
-		#				3rd pers. (indet.)	
+		#				3rd pers. (indet.)
 		"am"	=> "are",	"are"	=> "are",	"is"	 => "are",
 		"was"	=> "were",	"were"	=> "were",	"was"	 => "were",
 		"have"  => "have",	"have"  => "have",	"has"	 => "have",
@@ -336,7 +336,7 @@ module Linguistics::EN::Pluralization
 
 	PL_v_ambiguous_pres_h = {
 		#	1st pers. sing.		2nd pers. sing.		3rd pers. singular
-		#				3rd pers. (indet.)	
+		#				3rd pers. (indet.)
 		"act"	=> "act",	"act"	=> "act",	"acts"	  => "act",
 		"blame"	=> "blame",	"blame"	=> "blame",	"blames"  => "blame",
 		"can"	=> "can",	"can"	=> "can",	"can"	  => "can",
@@ -358,7 +358,7 @@ module Linguistics::EN::Pluralization
 	PL_v_ambiguous_pres = matchgroup PL_v_ambiguous_pres_h.keys
 
 	PL_v_irregular_non_pres = matchgroup %w[
-		did had ate made put 
+		did had ate made put
 		spent fought sank gave sought
 		shall could ought should
 	]
@@ -486,7 +486,7 @@ module Linguistics::EN::Pluralization
 	### examining the +original+ input.
 	def postprocess( original, inflected )
 
-		# If there's a classical variant, use it instead of the modern one if 
+		# If there's a classical variant, use it instead of the modern one if
 		# classical mode is on.
 		inflected.sub!( /([^|]+)\|(.+)/ ) do
 			Linguistics::EN.classical? ? $2 : $1
@@ -587,7 +587,7 @@ module Linguistics::EN::Pluralization
 			self.log.debug "  accusative pronoun; using PL_pron_acc table"
 			return PL_pron_acc_h[ word.downcase ]
 
-		# Handle isolated irregular plurals 
+		# Handle isolated irregular plurals
 		when /(.*)\b(#{PL_sb_irregular})$/i
 			prefix, word = $1, $2
 			self.log.debug "  isolated irregular; using PL_sb_irregular_h table"
@@ -701,7 +701,7 @@ module Linguistics::EN::Pluralization
 			self.log.debug "  yep, it's an irregular present tense verb (%p)" % [ key ]
 			return PL_v_irregular_pres_h[ $1.downcase ] + $2
 
-		# Handle irregular future, preterite and perfect tenses 
+		# Handle irregular future, preterite and perfect tenses
 		when /^(#{PL_v_irregular_non_pres})((\s.*)?)$/i
 			self.log.debug "  yep, it's an irregular non-present tense verb (%p)" % [ key ]
 			return word