spec/lib/tokenizers/base_spec.rb in picky-0.11.2 vs spec/lib/tokenizers/base_spec.rb in picky-0.12.0
- old
+ new
@@ -11,11 +11,11 @@
describe "substitute(s)_characters*" do
it "doesn't substitute if there is no substituter" do
@tokenizer.substitute_characters('abcdefghijklmnopqrstuvwxyzäöü').should == 'abcdefghijklmnopqrstuvwxyzäöü'
end
it "uses the substituter to replace characters" do
- @tokenizer.substitutes_characters_with CharacterSubstitution::European.new
+ @tokenizer.substitutes_characters_with CharacterSubstituters::WestEuropean.new
@tokenizer.substitute_characters('abcdefghijklmnopqrstuvwxyzäöü').should == 'abcdefghijklmnopqrstuvwxyzaeoeue'
end
it "uses the european substituter as default" do
@tokenizer.substitutes_characters_with
@@ -115,32 +115,9 @@
it "has remove_illegals" do
lambda { @tokenizer.remove_illegals('abcdefghijklmnop') }.should_not raise_error
end
it "removes illegal characters" do
@tokenizer.remove_illegals('abcdefghijklmnop').should == 'bcdeghijklmnp'
- end
- end
- end
-
- describe 'contracts_expressions' do
- context 'without contract_expressions called' do
- it 'should define a method contract' do
- lambda { @tokenizer.contract('from this text') }.should_not raise_error
- end
- it 'should define a method contract that does nothing' do
- unchanging = stub :unchanging
- @tokenizer.contract unchanging
- end
- end
- context 'with contracts_expressions called' do
- before(:each) do
- @tokenizer.contracts_expressions(/Mister|Mr./, 'mr')
- end
- it 'should define a method remove_stopwords' do
- lambda { @tokenizer.contract('from this text') }.should_not raise_error
- end
- it 'should define a method contract that contracts expressions' do
- @tokenizer.contract('Mister Meyer, Mr. Peter').should == 'mr Meyer, mr Peter'
end
end
end
describe 'stopwords' do
\ No newline at end of file