url_slicer 0.1.0

data/.document

@@ -0,0 +1,5 @@
+README.rdoc
+lib/**/*.rb
+bin/*
+features/**/*.feature
+LICENSE

data/.gitignore

@@ -0,0 +1,21 @@
+## MAC OS
+.DS_Store
+
+## TEXTMATE
+*.tmproj
+tmtags
+
+## EMACS
+*~
+\#*
+.\#*
+
+## VIM
+*.swp
+
+## PROJECT::GENERAL
+coverage
+rdoc
+pkg
+
+## PROJECT::SPECIFIC

data/LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2009 Simon Chiu
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.rdoc

@@ -0,0 +1,57 @@
+= URL Slicer
+
+I wanted a simple library to help me parse elements from a URL string, and thus I
+hacked away for a few hours and came up with URL Slicer.
+
+Acknowledgements:
+My regex know-how is a bit rusty, and so bits and pieces of the regex code to
+figure out the URL elements from the string are borrowed from various places
+from the internet. Unfortunately I do not remember where I got what code snippets.
+If you find parts of the regex that I've used here was what you have written, please e-mail me and I'll put your name down as a contributor.
+
+= Installation
+
+gem install url_slicer
+
+If you haven't already set up Gemcutter, simply go to http://gemcutter.org to learn 
+what you need to do.
+
+= Usage
+
+require 'url_slicer'
+include UrlSlicer
+
+url = UrlSlicer.new("http://www.google.com")
+
+url.valid?        # true
+
+url.host          # "www.google.com"
+
+url.domain        # "google.com"
+
+url.port          # 80
+
+url.ssl?          # false
+
+url.subdomain     # "www"
+
+url.protocol      # "http"
+
+If you've entered an invalid url, and subsequently try to call a method (eg. @instance_object.subdomain), it will raise UrlSlicer::InvalidUrlError, which you can
+resolve in your code.
+
+= Source Code
+
+The source can be found at http://github.com/tolatomeow/URL-Slicer. Please feel free
+to fork it and add your own features. Pull requests are welcomed.
+
+= License
+
+MIT license.
+
+= Contact
+skhchiu [at] gmail [dot] com
+
+== Copyright
+
+Copyright (c) 2009 Simon Chiu. See LICENSE for details.

data/Rakefile

@@ -0,0 +1,53 @@
+require 'rubygems'
+require 'rake'
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gem|
+    gem.name = "url_slicer"
+    gem.summary = %Q{Slices and dices URL strings into their elements}
+    gem.description = %Q{Easy and convenient methods to determine URL elements from a string}
+    gem.email = "skhchiu@gmail.com"
+    gem.homepage = "http://github.com/tolatomeow/URL-Slicer"
+    gem.authors = ["Simon Chiu"]
+    gem.add_development_dependency "shoulda", ">= 0"
+    # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
+  end
+  Jeweler::GemcutterTasks.new
+rescue LoadError
+  puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
+end
+
+require 'rake/testtask'
+Rake::TestTask.new(:test) do |test|
+  test.libs << 'lib' << 'test'
+  test.pattern = 'test/**/test_*.rb'
+  test.verbose = true
+end
+
+begin
+  require 'rcov/rcovtask'
+  Rcov::RcovTask.new do |test|
+    test.libs << 'test'
+    test.pattern = 'test/**/test_*.rb'
+    test.verbose = true
+  end
+rescue LoadError
+  task :rcov do
+    abort "RCov is not available. In order to run rcov, you must: sudo gem install spicycode-rcov"
+  end
+end
+
+task :test => :check_dependencies
+
+task :default => :test
+
+require 'rake/rdoctask'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "url_slicer #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION

@@ -0,0 +1 @@
+0.1.0

data/lib/url_slicer.rb

@@ -0,0 +1,64 @@
+class UrlSlicer
+  
+  class InvalidUrlError < StandardError; end;
+
+  attr_reader :url  
+  def initialize(url)
+    @url = url
+  end
+  
+  def valid?
+    regex = /\A(https?|ftp|file):\/\/.+\Z/
+    @valid ||= url.scan(regex).length > 0 ? true : false
+  end
+  
+  def host
+    raise InvalidUrlError unless valid?
+    regex = /\A[a-z][a-z0-9+\-.]*:\/\/([a-z0-9\-._~%!$&'()*+,;=]+@)?([a-z0-9\-._~%]+|\[[a-z0-9\-._~%!$&'()*+,;=:]+\])/
+    @host ||= url.scan(regex).flatten.compact.to_s
+  end
+  
+  def domain
+    raise InvalidUrlError unless valid?
+    regex = /^(?:(?>[a-z0-9-]*\.)+?|)([a-z0-9-]+\.(?>[a-z]*(?>\.[a-z]{2})?))$/i
+    @domain ||= host.scan(regex).to_s
+  end
+  
+  def subdomain
+    raise InvalidUrlError unless valid?
+    @subdomain ||= host.gsub(domain, '').gsub('.', '')
+  end
+  
+  def port
+    raise InvalidUrlError unless valid?
+    regex = /^[a-z][a-z0-9+\-.]*:\/\/([a-z0-9\-._~%!$&'()*+,;=]+@)?([a-z0-9\-._~%]+|\[[a-z0-9\-._~%!$&'()*+,;=:]+\]):([0-9]+)/
+    @port ||= url.scan(regex).flatten.compact[1].to_i
+    
+    @port == 0 ? default_port : @port
+  end
+  
+  def default_port
+    case protocol
+    when "http"
+      80
+    when "https"
+      443
+    when "ftp"  
+      21
+    else
+      nil
+    end
+  end
+  
+  def protocol
+    raise InvalidUrlError unless valid?
+    regex = /^(https|http|ftp|file)/
+    @protocol ||= url.scan(regex).flatten[0]
+  end
+  
+  def ssl?
+    raise InvalidUrlError unless valid?
+    protocol == "https" ? true : false
+  end
+  
+end

data/test/helper.rb

@@ -0,0 +1,10 @@
+require 'rubygems'
+require 'test/unit'
+require 'shoulda'
+
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+require 'url_slicer'
+
+class Test::Unit::TestCase
+end

data/test/test_url_slicer.rb

@@ -0,0 +1,139 @@
+require 'helper'
+
+class TestUrlSlicer < Test::Unit::TestCase
+  context "validating URL" do
+    should "be valid if url is http://www.test.com" do
+      url = UrlSlicer.new("http://www.test.com")
+      assert url.valid?
+    end
+    
+    should "be valid if url is ftp://ftp.test.com" do
+      url = UrlSlicer.new("ftp://ftp.test.com")
+      assert url.valid?
+    end
+    
+    should "not be valid if url is www" do
+      url = UrlSlicer.new("www")
+      assert !url.valid?
+    end
+    
+    should "not be valid if url is http://" do
+      url = UrlSlicer.new("http://")
+      assert !url.valid?
+    end
+    
+    should "be valid if url is http://localhost:3000" do
+      url = UrlSlicer.new("http://localhost:3000")
+      assert url.valid?
+    end
+  end
+  
+  context "returning host" do
+    should "return www.test.com if url is http://www.test.com" do
+      url = UrlSlicer.new("http://www.test.com")
+      assert_equal "www.test.com", url.host
+    end
+    
+    should "return www.test.com if url is http://www.test.com:80" do
+      url = UrlSlicer.new("http://www.test.com")
+      assert_equal "www.test.com", url.host
+    end
+    
+    should "return localhost if url is http://localhost:3000" do
+      url = UrlSlicer.new("http://localhost:3000")
+      assert_equal "localhost", url.host
+    end
+    
+    should "raise error if invalid url http:/www.test.com is entered" do
+      url = UrlSlicer.new("http:/www.test.com")
+      assert_raise UrlSlicer::InvalidUrlError do
+        assert_equal "www.test.com", url.host
+      end
+    end
+  end
+  
+  context "returning tld domain" do
+    should "return test.com if url is http://www.test.com" do
+      url = UrlSlicer.new("http://www.test.com")
+      assert_equal "test.com", url.domain
+    end
+    
+    should "return bbc.co.uk if url is http://www.bbc.co.uk" do
+      url = UrlSlicer.new("http://www.bbc.co.uk")
+      assert_equal "bbc.co.uk", url.domain
+    end
+    
+    should "return test.com if url is http://www.test.com:80" do
+      url = UrlSlicer.new("http://www.test.com")
+      assert_equal "test.com", url.domain
+    end
+  end
+  
+  context "returning subdomain" do
+    should "return www if url is http://www.test.com" do
+      url = UrlSlicer.new("http://www.test.com")
+      assert_equal "www", url.subdomain
+    end
+    
+    should "return blog if url is http://blog.somewhere.co.uk" do
+      url = UrlSlicer.new("http://blog.somewhere.co.uk")
+      assert_equal "blog", url.subdomain
+    end
+  end
+  
+  context "returning port" do
+    should "return port 80 if url is http://www.test.com:80" do
+      url = UrlSlicer.new("http://www.test.com:80")
+      assert_equal 80, url.port
+    end
+    
+    should "return port 8080 if url is http://www.bbc.co.uk:8080" do
+      url = UrlSlicer.new("http://www.bbc.co.uk:8080")
+      assert_equal 8080, url.port
+    end
+    
+    should "return port 80 if url is http://www.test.com" do
+      url = UrlSlicer.new("http://www.test.com")
+      assert_equal 80, url.port
+    end
+    
+    should "return port 21 if url is ftp://ftp.ucberkley.edu" do
+      url = UrlSlicer.new("ftp://ftp.ucberkley.edu")
+      assert_equal 21, url.port
+    end
+    
+    should "return port 443 if url is https://gmail.com" do
+      url = UrlSlicer.new("https://gmail.com")
+      assert_equal 443, url.port
+    end
+  end
+  
+  context "protocol" do
+    should "return http if url is http://www.test.com" do
+      url = UrlSlicer.new("http://www.test.com")
+      assert_equal "http", url.protocol
+    end
+    
+    should "return https if url is https://gmail.com" do
+      url = UrlSlicer.new("https://gmail.com")
+      assert_equal "https", url.protocol
+    end
+    
+    should "return ftp if url is ftp://ftp.ucberkley.edu" do
+      url = UrlSlicer.new("ftp://ftp.ucberkley.edu")
+      assert_equal "ftp", url.protocol
+    end
+  end
+  
+  context "ssl" do
+    should "return true if url is https://www.test.com" do
+      url = UrlSlicer.new("https://www.test.com")
+      assert url.ssl?
+    end
+    
+    should "return false if url is http://www.test.com" do
+      url = UrlSlicer.new("http://www.test.com")
+      assert !url.ssl?
+    end
+  end
+end

metadata

@@ -0,0 +1,74 @@
+--- !ruby/object:Gem::Specification 
+name: url_slicer
+version: !ruby/object:Gem::Version 
+  version: 0.1.0
+platform: ruby
+authors: 
+- Simon Chiu
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2009-11-29 00:00:00 -05:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: shoulda
+  type: :development
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: "0"
+    version: 
+description: Easy and convenient methods to determine URL elements from a string
+email: skhchiu@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- LICENSE
+- README.rdoc
+files: 
+- .document
+- .gitignore
+- LICENSE
+- README.rdoc
+- Rakefile
+- VERSION
+- lib/url_slicer.rb
+- test/helper.rb
+- test/test_url_slicer.rb
+has_rdoc: true
+homepage: http://github.com/tolatomeow/URL-Slicer
+licenses: []
+
+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: 1.3.5
+signing_key: 
+specification_version: 3
+summary: Slices and dices URL strings into their elements
+test_files: 
+- test/helper.rb
+- test/test_url_slicer.rb