Fix breaking changes (#87)

* fix gsl warning spam

* wip fixe breaking changes, to be not so breaking

* convert raise to warning

classifier-reborn.gemspec

@@ -30,6 +30,8 @@ Gem::Specification.new do |s|
 
   s.add_development_dependency('rake')
   s.add_development_dependency('rdoc')
-  s.add_development_dependency('test-unit')
+  s.add_development_dependency('minitest')
+  s.add_development_dependency('minitest-reporters')
   s.add_development_dependency('rubocop')
+  s.add_development_dependency('pry')
 end

lib/classifier-reborn/lsi.rb

@@ -5,11 +5,12 @@
 begin
   raise LoadError if ENV['NATIVE_VECTOR'] == 'true' # to test the native vector class, try `rake test NATIVE_VECTOR=true`
 
-  require 'gsl' # requires https://github.com/blackwinter/rb-gsl
+  require 'gsl' # requires https://github.com/SciRuby/rb-gsl
   require_relative 'extensions/vector_serialize'
   $GSL = true
 
 rescue LoadError
+  $GSL = false
   require_relative 'extensions/vector'
 end
 
@@ -65,15 +66,16 @@ def needs_rebuild?
     def add_item(item, *categories, &block)
       clean_word_hash = Hasher.clean_word_hash((block ? block.call(item) : item.to_s), @language)
       if clean_word_hash.empty?
-        raise "#{item} is composed entirely of stopwords and words that are 2 characters or less. Classifier-Reborn cannot handle this document properly, and thus summarily rejected it."
+        puts "Input: '#{item}' is entirely stopwords or words with 2 or fewer characters. Classifier-Reborn cannot handle this document properly."
+      else
+        @items[item] = if @cache_node_vectors
+                         CachedContentNode.new(clean_word_hash, *categories)
+                       else
+                         ContentNode.new(clean_word_hash, *categories)
+                       end
+        @version += 1
+        build_index if @auto_rebuild
       end
-      @items[item] = if @cache_node_vectors
-                       CachedContentNode.new(clean_word_hash, *categories)
-                     else
-                       ContentNode.new(clean_word_hash, *categories)
-                     end
-      @version += 1
-      build_index if @auto_rebuild
     end
 
     # A less flexible shorthand for add_item that assumes
@@ -203,11 +205,14 @@ def proximity_norms_for_content(doc, &block)
       return [] if needs_rebuild?
 
       content_node = node_for_content(doc, &block)
-
       if $GSL && content_node.raw_norm.isnan?.all?
-        raise "There are no documents that are similar to #{doc}"
+        puts "There are no documents that are similar to #{doc}"
+      else
+        content_node_norms(content_node)
       end
+    end
 
+    def content_node_norms(content_node)
       result =
         @items.keys.collect do |item|
           if $GSL
@@ -230,8 +235,10 @@ def proximity_norms_for_content(doc, &block)
     def search(string, max_nearest = 3)
       return [] if needs_rebuild?
       carry = proximity_norms_for_content(string)
-      result = carry.collect { |x| x[0] }
-      result[0..max_nearest - 1]
+      unless carry.nil?
+        result = carry.collect { |x| x[0] }
+        result[0..max_nearest - 1]
+      end
     end
 
     # This function takes content and finds other documents

test/bayes/bayesian_test.rb

@@ -1,29 +1,29 @@
 # encoding: utf-8
 
 require File.dirname(__FILE__) + '/../test_helper'
-class BayesianTest < Test::Unit::TestCase
+class BayesianTest < Minitest::Test
   def setup
     @classifier = ClassifierReborn::Bayes.new 'Interesting', 'Uninteresting'
   end
 
   def test_good_training
-    assert_nothing_raised { @classifier.train_interesting 'love' }
+     assert_equal ['love'], @classifier.train_interesting('love')
   end
 
   def test_training_with_utf8
-    assert_nothing_raised { @classifier.train_interesting 'Água' }
+    assert_equal ['Água'], @classifier.train_interesting('Água')
   end
 
   def test_stemming_enabled_by_default
     assert @classifier.stemmer_enabled?
   end
 
   def test_bad_training
-    assert_raise(StandardError) { @classifier.train_no_category 'words' }
+    assert_raises(StandardError) { @classifier.train_no_category 'words' }
   end
 
   def test_bad_method
-    assert_raise(NoMethodError) { @classifier.forget_everything_you_know '' }
+    assert_raises(NoMethodError) { @classifier.forget_everything_you_know '' }
   end
 
   def test_categories
@@ -120,6 +120,6 @@ def test_untrain
     classification_of_bad_data = @classifier.classify 'seven'
     @classifier.untrain_colors 'seven'
     classification_after_untrain = @classifier.classify 'seven'
-    assert_not_equal classification_of_bad_data, classification_after_untrain
+    refute_equal classification_of_bad_data, classification_after_untrain
   end
 end

test/extensions/hasher_test.rb

@@ -1,7 +1,7 @@
 require_relative '../test_helper'
 require 'tempfile'
 
-class HasherTest < Test::Unit::TestCase
+class HasherTest < Minitest::Test
   def setup
     @original_stopwords_path = Hasher::STOPWORDS_PATH.dup
   end
@@ -22,8 +22,8 @@ def test_clean_word_hash_without_stemming
   end
 
   def test_default_stopwords
-    assert_not_empty Hasher::STOPWORDS['en']
-    assert_not_empty Hasher::STOPWORDS['fr']
+    refute_empty Hasher::STOPWORDS['en']
+    refute_empty Hasher::STOPWORDS['fr']
     assert_empty Hasher::STOPWORDS['gibberish']
   end
 
@@ -38,17 +38,17 @@ def test_loads_custom_stopwords
 
     custom_english_stopwords = Hasher::STOPWORDS['en']
 
-    assert_not_equal default_english_stopwords, custom_english_stopwords
+    refute_equal default_english_stopwords, custom_english_stopwords
   end
 
   def test_add_custom_stopword_path
     # Create stopword tempfile in current directory
     temp_stopwords = Tempfile.new('xy', "#{File.dirname(__FILE__) + "/"}")
-    
+
     # Add some stopwords to tempfile
     temp_stopwords << "this words fun"
-    temp_stopwords.close 
-    
+    temp_stopwords.close
+
     # Get path of tempfile
     temp_stopwords_path = File.dirname(temp_stopwords)
 

test/lsi/lsi_test.rb

@@ -1,6 +1,6 @@
 require File.dirname(__FILE__) + '/../test_helper'
 
-class LSITest < Test::Unit::TestCase
+class LSITest < Minitest::Test
   def setup
     # we repeat principle words to help weight them.
     # This test is rather delicate, since this system is mostly noise.
@@ -86,7 +86,7 @@ def test_external_classifying
     # will fail here, but the LSI recognizes content.
     tricky_case = 'This text revolves around dogs.'
     assert_equal 'Dog', lsi.classify(tricky_case)
-    assert_not_equal 'Dog', bayes.classify(tricky_case)
+    refute_equal 'Dog', bayes.classify(tricky_case)
   end
 
   def test_recategorize_interface
@@ -189,16 +189,12 @@ def test_invalid_searching_when_using_gsl
     lsi.add_item @str3, 'Cat'
     lsi.add_item @str4, 'Cat'
     lsi.add_item @str5, 'Bird'
-    assert_raises RuntimeError do
-      lsi.search('penguin')
-    end
+    assert_output(/There are no documents that are similar to penguin/) { lsi.search('penguin') }
   end
 
-  def test_raise_error_when_adding_bad_document
+  def test_warn_when_adding_bad_document
     lsi = ClassifierReborn::LSI.new
-    assert_raises RuntimeError do
-      lsi.add_item("i can")
-    end
+    assert_output(/Input: 'i can' is entirely stopwords or words with 2 or fewer characters. Classifier-Reborn cannot handle this document properly./) { lsi.add_item("i can") }
   end
 
   def test_summary

test/lsi/word_list_test.rb

@@ -1,6 +1,6 @@
 require_relative '../test_helper'
 
-class WordListTest < Test::Unit::TestCase
+class WordListTest < Minitest::Test
   def test_size_does_not_count_words_twice
     list = ClassifierReborn::WordList.new
     assert list.size == 0

test/test_helper.rb

@@ -1,6 +1,8 @@
 $LOAD_PATH.unshift(File.dirname(__FILE__) + '/../lib')
 
-require 'test/unit'
+require 'minitest/autorun'
+require 'minitest/reporters'
+Minitest::Reporters.use!
+require 'pry'
 require 'classifier-reborn'
-
 include ClassifierReborn