fizx-stringset 0.2.0

data/spec/spec_helper.rb

@@ -0,0 +1,11 @@
+require "rubygems"
+require 'spec'
+require "benchmark"
+
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+require 'stringset'
+
+Spec::Runner.configure do |config|
+  
+end

data/spec/stringset_spec.rb

@@ -0,0 +1,67 @@
+require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
+
+describe "StringSet" do
+  describe "#new" do
+    it "should accept a string and tokenize it" do
+      s = StringSet.new "tokenize me"
+      s.strings.should == %w[tokenize me]
+    end
+    
+    it "should accept an array of tokens" do 
+      s = StringSet.new %w[tokenized list]
+      s.strings.should == %w[tokenized list]
+    end
+    
+    it "could accept an array of multi-word tokens" do
+      s = StringSet.new ["foo bar", "bar"]
+    end
+    
+    it "should know the max token length of the multiword tokenset" do
+      s = StringSet.new ["foo bar", "bar"]
+      s.max_token_size.should == 2
+    end
+    
+    it "should have the option to stem" do
+      s = StringSet.new %w[tokenized list], :stem => true
+      s.should be_stemming
+    end
+  end
+  
+  describe "#ngramize" do
+    it "should make the correct ngrams" do
+      s = StringSet.new
+      s.ngramize(%w[a b c d], 3).should == ["a", "b", "c", "d", "a b", "b c", "c d", "a b c", "b c d"]
+    end
+  end
+  
+  describe "#substrings_in" do
+    it "should return a list of common substrings" do
+      s = StringSet.new "tokenize me"
+      s.substrings_in("can you please tokenize me?").should == %w[tokenize me]
+    end
+    
+    it "should handle multiword substrings" do
+      s = StringSet.new ["tokenize me"]
+      s.substrings_in("can you please tokenize me?").should == ["tokenize me"]
+    end
+    
+    it "should handle multiword substrings with stemming" do
+      s = StringSet.new ["tokenize me"], :stem => true
+      s.substrings_in("can you please tokenize me?").should == ["token me"]
+    end
+    
+    it "should account for stemming" do 
+      s = StringSet.new "token me", :stem => true
+      s.substrings_in("can you please tokenize me?").should == %w[token me]
+    end
+    
+    it "should be pretty fast" do
+      needles = %[love thine soldiers bananas monkeys bachelors masters doctorate]
+      hamlet = File.read(File.join(File.dirname(__FILE__), "hamlet.txt"))
+      Benchmark.measure do
+        s = StringSet.new(needles)
+        s.substrings_in(hamlet)
+      end.real.should < 0.1
+    end
+  end
+end

metadata

@@ -0,0 +1,62 @@
+--- !ruby/object:Gem::Specification 
+name: fizx-stringset
+version: !ruby/object:Gem::Version 
+  version: 0.2.0
+platform: ruby
+authors: 
+- Kyle Maxwell
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2009-06-04 00:00:00 -07:00
+default_executable: 
+dependencies: []
+
+description: 
+email: kyle@kylemaxwell.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- LICENSE
+- README.rdoc
+files: 
+- LICENSE
+- README.rdoc
+- Rakefile
+- VERSION.yml
+- lib/stringset.rb
+- spec/hamlet.txt
+- spec/spec_helper.rb
+- spec/stringset_spec.rb
+has_rdoc: true
+homepage: http://github.com/fizx/stringset
+post_install_message: 
+rdoc_options: 
+- --charset=UTF-8
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.2.0
+signing_key: 
+specification_version: 2
+summary: TODO
+test_files: 
+- spec/spec_helper.rb
+- spec/stringset_spec.rb