luisparravicini-classifier 1.4.1 → 1.4.2

data/VERSION.yml

@@ -1,5 +1,5 @@
 --- 
-:build: 
-:patch: 1
 :major: 1
 :minor: 4
+:patch: 2
+:build: 

data/lib/classifier/base.rb

@@ -10,7 +10,7 @@ module Classifier
     end
   
     def prepare_category_name val
-      val.to_s.gsub("_"," ").capitalize.intern 
+      val.to_s.gsub("_"," ").capitalize
     end
     
     # Removes common punctuation symbols, returning a new string. 
@@ -22,7 +22,7 @@ module Classifier
     end
     
     # Return a Hash of strings => ints. Each word in the string is stemmed,
-    # interned, and indexes to its frequency in the document.  
+    # and indexes to its frequency in the document.  
   	def word_hash str
   		word_hash_for_words(str.gsub(/[^\w\s]/,"").split + str.gsub(/[\w]/," ").split)
   	end
@@ -50,9 +50,11 @@ module Classifier
   	def word_hash_for_words(words)
   		d = Hash.new
   		skip_words = StopWords.for(@options[:language], @options[:lang_dir])
+      encoding_name = @options[:encoding].gsub(/_/, '-')
   		words.each do |word|
   			word = word.mb_chars.downcase.to_s if word =~ /[\w]+/
-  			key = stemmer.stem(word).intern
+  			key = stemmer.stem(word)
+        key.force_encoding(encoding_name)
   			if word =~ /[^\w]/ || ! skip_words.include?(word) && word.length > 2
   				d[key] ||= 0
   				d[key] += 1

data/luisparravicini-classifier.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{luisparravicini-classifier}
-  s.version = "1.4.1"
+  s.version = "1.4.2"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Luis Parravicini"]
-  s.date = %q{2010-01-29}
+  s.date = %q{2010-02-02}
   s.description = %q{Bayesian classifier and others.}
   s.email = %q{lparravi@gmail.com}
   s.extra_rdoc_files = [

data/test/base_test.rb

@@ -3,14 +3,14 @@ class HelpersTest < Test::Unit::TestCase
   
 	def test_word_hash
 	  c = Classifier::Base.new
-		hash = {:good=>1, :"!"=>1, :hope=>1, :"'"=>1, :"."=>1, :love=>1, :word=>1, :them=>1, :test=>1}
+		hash = {'good'=>1, "!"=>1, 'hope'=>1, "'"=>1, "."=>1, 'love'=>1, 'word'=>1, 'them'=>1, 'test'=>1}
 		assert_equal hash, c.word_hash("here are some good words of test's. I hope you love them!")
 	end
 
    	
 	def test_clean_word_hash
 	  c = Classifier::Base.new
-	  hash = {:good=>1, :word=>1, :hope=>1, :love=>1, :them=>1, :test=>1}
+	  hash = {'good'=>1, 'word'=>1, 'hope'=>1, 'love'=>1, 'them'=>1, 'test'=>1}
 	  assert_equal hash, c.clean_word_hash("here are some good words of test's. I hope you love them!")
 	end
 

data/test/lsi/lsi_test.rb

@@ -157,11 +157,11 @@ class LSITest < Test::Unit::TestCase
 	  lsi.add_item @str4, "Cat"
 	  lsi.add_item @str5, "Bird"
 	
-	  assert_equal [:dog, :text, :deal], lsi.highest_ranked_stems(@str1)
+	  assert_equal ['dog', 'text', 'deal'], lsi.highest_ranked_stems(@str1)
 	end
 	
 	def test_summary
 	   assert_equal "This text involves dogs too [...] This text also involves cats", [@str1, @str2, @str3, @str4, @str5].join.summary(2)
 	end
 	  
-end
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: luisparravicini-classifier
 version: !ruby/object:Gem::Version 
-  version: 1.4.1
+  version: 1.4.2
 platform: ruby
 authors: 
 - Luis Parravicini
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-01-29 00:00:00 -02:00
+date: 2010-02-02 00:00:00 -02:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency