englishext 0.1.0 → 0.1.1

data/lib/englishext.rb

@@ -1,6 +1,6 @@
 # A collection of English-language specific utility methods.
 module EnglishExtensions
-	Version = '0.1.0'
+	Version = '0.1.1'
 end
 
 class String
@@ -53,15 +53,20 @@ class String
 	#   "bosnia and herzegovina".proper_noun -> "Bosnia and Herzegovina"
 	#   "macedonia, the former yugoslav republic of".proper_noun ->
 	#     "Macedonia, the Former Yugoslav Republic of"
-	#   "virgin islands, u.s.".proper_noun -> "Virgin Islands, U.S."
+	#   "virgin islands, u.s.".proper_noun -> "Virgin Islands, U.S."	
 	def proper_noun
 		proper_noun = ""
 		str = self.clone
-		while(matchIndex = str =~ /[\. ]/)
-			word = str[0..matchIndex-1]
-			word = word.capitalize unless [ 'and', 'the', 'of' ].index(word) != nil
-			proper_noun += word + $&
-			str = str[matchIndex+1..str.length]
+		while(matchIndex = str =~ /[\. \-\']/)
+			if matchIndex == 0
+				proper_noun += $&
+				str = str[matchIndex+1..str.length]
+			else
+				word = str[0..matchIndex-1]
+				word = word.capitalize unless [ 'and', 'the', 'of' ].index(word) != nil
+				proper_noun += word + $&
+				str = str[matchIndex+1..str.length]
+			end
 		end
 		word = str
 		word = word.capitalize unless [ 'and', 'the', 'of' ].index(word) != nil

data/lib/englishext.rb~

@@ -0,0 +1,124 @@
+# A collection of English-language specific utility methods.
+module EnglishExtensions
+	Version = '0.1.0'
+end
+
+class String
+	# Turns a camel-case string ("camel_case_to_english") to plain English
+	# ("camel case to english"). Each word is decapitalized.
+	def camel_case_to_english
+		words = []
+		str = self.clone
+		nextCapIndex =(str =~ /[A-Z]/)
+		while nextCapIndex != nil
+			words << $` if $`.size > 0
+			str = $& + $'
+			str[0] = str[0..0].downcase
+			nextCapIndex =(str =~ /[A-Z]/)
+		end
+		words << str
+		words.join ' '
+	end
+	
+	# Turns an English language string into camel case.
+	def english_to_camel_case
+		cc = ""
+		split.each { |word|
+			word = word.capitalize unless cc == ''
+			cc = cc += word
+		}
+		cc
+	end
+	
+	# Given a singular noun, returns the plural form.
+	def plural
+		consonantYPattern = Regexp.new("([^aeiou])y$", Regexp::IGNORECASE)
+		if self =~ consonantYPattern
+			self.gsub consonantYPattern, '\1ies'
+		elsif self =~ /^(.*)xis$/
+			$1 + 'xes'
+		elsif self =~ /[xs]$/
+			self + "es"
+		elsif self =~ /(.*)tum$/
+			$1 + 'ta'
+		else
+			self + "s"
+		end
+	end
+
+	# Returns the proper noun form of a string by capitalizing most of the 
+	# words.
+	#
+	# Examples:
+	#   "bosnia and herzegovina".proper_noun -> "Bosnia and Herzegovina"
+	#   "macedonia, the former yugoslav republic of".proper_noun ->
+	#     "Macedonia, the Former Yugoslav Republic of"
+	#   "virgin islands, u.s.".proper_noun -> "Virgin Islands, U.S."
+	def proper_noun
+		proper_noun = ""
+		str = self.clone
+		while(matchIndex = str =~ /[\. ]/)
+			word = str[0..matchIndex-1]
+			word = word.capitalize unless [ 'and', 'the', 'of' ].index(word) != nil
+			proper_noun += word + $&
+			str = str[matchIndex+1..str.length]
+		end
+		word = str
+		word = word.capitalize unless [ 'and', 'the', 'of' ].index(word) != nil
+		proper_noun += word
+		proper_noun
+	end
+
+	def singular
+		if self =~ /(.*)ies/
+			$1 + 'y'
+		elsif self =~ /(.*s)es/
+			$1
+		else
+			self =~ /(.*)s/
+			$1
+		end
+	end
+
+	# Does this word start with a vowel sound? "User" and "usury" don't, but 
+	# "ugly" does.
+	def starts_with_vowel_sound
+		uSomethingUMatch = self =~ /^u[^aeiuo][aeiou]/
+		# 'user' and 'usury' don't start with a vowel sound
+		self =~ /^[aeiou]/ && !uSomethingUMatch
+	end
+
+	# Given a format for a template sentence, generates the sentence while 
+	# accounting for details such as pluralization and whether to use "a" or 
+	# "an".
+	#
+	# Format codes are:
+	#          * %num: Number
+	#          * %is: Transitive verb. This will be turned into "is" or "are", 
+	#            depending on <tt>number</tt>.
+	#          * %nam: Name. This will be rendered as either singular or 
+	#            plural, depending on <tt>number</tt>.
+	#          * %a: Indefinite article. This will be turned into "a" or "an", 
+	#            depending on <tt>name</tt>.
+	# [name] The name of the object being described.
+	# [number] The number of the objects being describes.
+	#
+	# Examples:
+	#   "There %is currently %num %nam".template( "product category", 0 ) ->
+	#       "There are currently 0 product categories"
+	#   "There %is currently %num %nam".template( "product category", 1 ) ->
+	#       "There is currently 1 product category"
+	#   "Add %a %nam".template( "invoice" ) -> "Add an invoice"	
+	def template( name, number = 1)
+		sentence = clone
+		sentence.gsub!( /%num/, number.to_s )
+		isVerb = number == 1 ? "is" : "are"
+		sentence.gsub!( /%is/, isVerb )
+		name = name.plural if number != 1
+		sentence.gsub!( /%nam/, name )
+		article = name.starts_with_vowel_sound ? 'an' : 'a'
+		sentence.gsub!( /%a/, article )
+		sentence
+	end
+end
+

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
-rubygems_version: 0.8.6
+rubygems_version: 0.8.11
 specification_version: 1
 name: englishext
 version: !ruby/object:Gem::Version 
-  version: 0.1.0
-date: 2005-07-03
+  version: 0.1.1
+date: 2006-08-20 00:00:00 -04:00
 summary: EnglishExtensions contains a few convenience methods for String.
 require_paths: 
-  - lib
+- lib
 email: sera@fhwang.net
 homepage: http://englishext.rubyforge.org/
 rubyforge_project: 
@@ -18,20 +18,29 @@ bindir: bin
 has_rdoc: false
 required_ruby_version: !ruby/object:Gem::Version::Requirement 
   requirements: 
-    - 
-      - ">"
-      - !ruby/object:Gem::Version 
-        version: 0.0.0
+  - - ">"
+    - !ruby/object:Gem::Version 
+      version: 0.0.0
   version: 
 platform: ruby
+signing_key: 
+cert_chain: 
 authors: 
-  - Francis Hwang
+- Francis Hwang
 files: 
-  - lib/englishext.rb
+- lib/englishext.rb
+- lib/englishext.rb~
 test_files: []
+
 rdoc_options: []
+
 extra_rdoc_files: []
+
 executables: []
+
 extensions: []
+
 requirements: []
-dependencies: []
+
+dependencies: []
+