f1sherman-domainatrix 0.0.10

data/spec/domainatrix/domain_parser_spec.rb

@@ -0,0 +1,71 @@
+require File.dirname(__FILE__) + '/../spec_helper'
+
+describe "domain parser" do
+  before(:all) do
+    @domain_parser = Domainatrix::DomainParser.new("#{File.dirname(__FILE__)}/../../lib/effective_tld_names.dat")
+  end
+
+  describe "reading the dat file" do
+    it "creates a tree of the domain names" do
+      @domain_parser.public_suffixes.should be_a Hash
+    end
+
+    it "creates the first level of the tree" do
+      @domain_parser.public_suffixes.should have_key("com")
+    end
+
+    it "creates the first level of the tree even when the first doesn't appear on a line by itself" do
+      @domain_parser.public_suffixes.should have_key("uk")
+    end
+
+    it "creates lower levels of the tree" do
+      @domain_parser.public_suffixes["jp"].should have_key("ac")
+      @domain_parser.public_suffixes["jp"]["aichi"].should have_key("*")
+    end
+  end
+
+  describe "parsing" do
+    it "returns a hash of parts" do
+      @domain_parser.parse("http://pauldix.net").should be_a Hash
+    end
+
+    it "includes the original url" do
+      @domain_parser.parse("http://www.pauldix.net")[:url].should == "http://www.pauldix.net"
+    end
+
+    it "includes the scheme" do
+      @domain_parser.parse("http://www.pauldix.net")[:scheme].should == "http"
+    end
+    
+    it "includes the full host" do
+      @domain_parser.parse("http://www.pauldix.net")[:host].should == "www.pauldix.net"      
+    end
+    
+    it "parses out the path" do
+      @domain_parser.parse("http://pauldix.net/foo.html?asdf=foo")[:path].should == "/foo.html?asdf=foo"
+      @domain_parser.parse("http://pauldix.net?asdf=foo")[:path].should == "?asdf=foo"
+      @domain_parser.parse("http://pauldix.net")[:path].should == ""
+    end
+
+    it "parses the tld" do
+      @domain_parser.parse("http://pauldix.net")[:public_suffix].should == "net"
+      @domain_parser.parse("http://pauldix.co.uk")[:public_suffix].should == "co.uk"
+      @domain_parser.parse("http://pauldix.com.kg")[:public_suffix].should == "com.kg"
+      @domain_parser.parse("http://pauldix.com.aichi.jp")[:public_suffix].should == "com.aichi.jp"
+    end
+
+    it "should have the domain" do
+      @domain_parser.parse("http://pauldix.net")[:domain].should == "pauldix"
+      @domain_parser.parse("http://foo.pauldix.net")[:domain].should == "pauldix"
+      @domain_parser.parse("http://pauldix.co.uk")[:domain].should == "pauldix"
+      @domain_parser.parse("http://foo.pauldix.co.uk")[:domain].should == "pauldix"
+      @domain_parser.parse("http://pauldix.com.kg")[:domain].should == "pauldix"
+      @domain_parser.parse("http://pauldix.com.aichi.jp")[:domain].should == "pauldix"
+    end
+
+    it "should have subdomains" do
+      @domain_parser.parse("http://foo.pauldix.net")[:subdomain].should == "foo"
+      @domain_parser.parse("http://bar.foo.pauldix.co.uk")[:subdomain].should == "bar.foo"
+    end
+  end
+end

data/spec/domainatrix/url_spec.rb

@@ -0,0 +1,54 @@
+require File.dirname(__FILE__) + '/../spec_helper'
+
+describe "url" do
+  it "has the original url" do
+    Domainatrix::Url.new(:url => "http://pauldix.net").url.should == "http://pauldix.net"
+  end
+
+  it "has the public_suffix" do
+    Domainatrix::Url.new(:public_suffix => "net").public_suffix.should == "net"
+  end
+
+  it "has the domain" do
+    Domainatrix::Url.new(:domain => "pauldix").domain.should == "pauldix"
+  end
+
+  it "has the subdomain" do
+    Domainatrix::Url.new(:subdomain => "foo").subdomain.should == "foo"
+  end
+
+  it "has the path" do
+    Domainatrix::Url.new(:path => "/asdf.html").path.should == "/asdf.html"
+  end
+
+  it "canonicalizes the url" do
+    Domainatrix::Url.new(:domain => "pauldix", :public_suffix => "net").canonical.should == "net.pauldix"
+    Domainatrix::Url.new(:subdomain => "foo", :domain => "pauldix", :public_suffix => "net").canonical.should == "net.pauldix.foo"
+    Domainatrix::Url.new(:subdomain => "foo.bar", :domain => "pauldix", :public_suffix => "net").canonical.should == "net.pauldix.bar.foo"
+    Domainatrix::Url.new(:domain => "pauldix", :public_suffix => "co.uk").canonical.should == "uk.co.pauldix"
+    Domainatrix::Url.new(:subdomain => "foo", :domain => "pauldix", :public_suffix => "co.uk").canonical.should == "uk.co.pauldix.foo"
+    Domainatrix::Url.new(:subdomain => "foo.bar", :domain => "pauldix", :public_suffix => "co.uk").canonical.should == "uk.co.pauldix.bar.foo"
+    Domainatrix::Url.new(:subdomain => "", :domain => "pauldix", :public_suffix => "co.uk").canonical.should == "uk.co.pauldix"
+  end
+
+  it "canonicalizes the url with the path" do
+    Domainatrix::Url.new(:subdomain => "foo", :domain => "pauldix", :public_suffix => "net", :path => "/hello").canonical.should == "net.pauldix.foo/hello"
+  end
+
+  it "canonicalizes the url without the path" do
+    Domainatrix::Url.new(:subdomain => "foo", :domain => "pauldix", :public_suffix => "net").canonical(:include_path => false).should == "net.pauldix.foo"
+  end
+
+  it "combines the domain with the public_suffix" do
+    Domainatrix::Url.new(:domain => "pauldix", :public_suffix => "net").domain_with_public_suffix.should == "pauldix.net"
+    Domainatrix::Url.new(:domain => "foo", :public_suffix => "co.uk" ).domain_with_public_suffix.should == "foo.co.uk"
+    Domainatrix::Url.new(:subdomain => "baz", :domain => "bar", :public_suffix => "com").domain_with_public_suffix.should == "bar.com"
+  end
+  
+  it "combines the domain with the public_suffix as an alias" do
+    Domainatrix::Url.new(:domain => "pauldix", :public_suffix => "net").domain_with_tld.should == "pauldix.net"
+    Domainatrix::Url.new(:domain => "foo", :public_suffix => "co.uk" ).domain_with_tld.should == "foo.co.uk"
+    Domainatrix::Url.new(:subdomain => "baz", :domain => "bar", :public_suffix => "com").domain_with_tld.should == "bar.com"
+  end
+
+end

data/spec/domainatrix_spec.rb

@@ -0,0 +1,16 @@
+require File.dirname(__FILE__) + '/spec_helper'
+
+describe "domainatrix" do
+  it "should parse into a url object" do
+    Domainatrix.parse("http://pauldix.net").should be_a Domainatrix::Url
+  end
+
+  it "should canonicalize" do
+    Domainatrix.parse("http://pauldix.net").canonical.should == "net.pauldix"
+    Domainatrix.parse("http://pauldix.net/foo.html").canonical.should == "net.pauldix/foo.html"
+    Domainatrix.parse("http://pauldix.net/foo.html?asdf=bar").canonical.should == "net.pauldix/foo.html?asdf=bar"
+    Domainatrix.parse("http://foo.pauldix.net").canonical.should == "net.pauldix.foo"
+    Domainatrix.parse("http://foo.bar.pauldix.net").canonical.should == "net.pauldix.bar.foo"
+    Domainatrix.parse("http://pauldix.co.uk").canonical.should == "uk.co.pauldix"
+  end
+end

data/spec/spec.opts

@@ -0,0 +1,2 @@
+--diff
+--color

data/spec/spec_helper.rb

@@ -0,0 +1,10 @@
+require "rubygems"
+require "rspec"
+
+# gem install redgreen for colored test output
+begin require "redgreen" unless ENV['TM_CURRENT_LINE']; rescue LoadError; end
+
+path = File.expand_path(File.dirname(__FILE__) + "/../lib/")
+$LOAD_PATH.unshift(path) unless $LOAD_PATH.include?(path)
+
+require "#{File.dirname(__FILE__)}/../lib/domainatrix"

metadata

@@ -0,0 +1,87 @@
+--- !ruby/object:Gem::Specification 
+name: f1sherman-domainatrix
+version: !ruby/object:Gem::Version 
+  hash: 11
+  prerelease: 
+  segments: 
+  - 0
+  - 0
+  - 10
+  version: 0.0.10
+platform: ruby
+authors: 
+- Paul Dix
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2009-12-10 00:00:00 Z
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: addressable
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  type: :runtime
+  version_requirements: *id001
+description: 
+email: paul@pauldix.net
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- lib/domainatrix.rb
+- lib/effective_tld_names.dat
+- lib/domainatrix/domain_parser.rb
+- lib/domainatrix/url.rb
+- README.textile
+- spec/spec.opts
+- spec/spec_helper.rb
+- spec/domainatrix_spec.rb
+- spec/domainatrix/domain_parser_spec.rb
+- spec/domainatrix/url_spec.rb
+homepage: http://github.com/pauldix/domainatrix
+licenses: []
+
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.8.10
+signing_key: 
+specification_version: 2
+summary: A cruel mistress that uses the public suffix domain list to dominate URLs by canonicalizing, finding the public suffix, and breaking them into their domain parts.
+test_files: []
+