url_parser 0.4.0 → 0.5.0

data/lib/url_parser/uri.rb

@@ -0,0 +1,206 @@
+require 'forwardable'
+require 'resolv'
+
+module UrlParser
+  class URI
+    extend Forwardable
+
+    LOCALHOST_REGEXP  = /(\A|\.)localhost\z/
+
+    COMPONENTS = [
+      :scheme,              # Top level URI naming structure / protocol.
+      :username,            # Username portion of the userinfo.
+      :user,                # Alias for #username.
+      :password,            # Password portion of the userinfo.
+      :userinfo,            # URI username and password for authentication.
+      :hostname,            # Fully qualified domain name or IP address.
+      :naked_hostname,      # Hostname without any ww? prefix.
+      :port,                # Port number.
+      :host,                # Hostname and port.
+      :www,                 # The ww? portion of the subdomain.
+      :tld,                 # Returns the top level domain portion, aka the extension.
+      :top_level_domain,    # Alias for #tld.
+      :extension,           # Alias for #tld.
+      :sld,                 # Returns the second level domain portion, aka the domain part.
+      :second_level_domain, # Alias for #sld.
+      :domain_name,         # Alias for #sld.
+      :trd,                 # Returns the third level domain portion, aka the subdomain part.
+      :third_level_domain,  # Alias for #trd.
+      :subdomains,          # Alias for #trd.
+      :naked_trd,           # Any non-ww? subdomains.
+      :naked_subdomain,     # Alias for #naked_trd.
+      :domain,              # The domain name with the tld.
+      :subdomain,           # All subdomains, include ww?.
+      :origin,              # Scheme and host.
+      :authority,           # Userinfo and host.
+      :site,                # Scheme, userinfo, and host.
+      :path,                # Directory and segment.
+      :segment,             # Last portion of the path.
+      :directory,           # Any directories following the site within the URI.
+      :filename,            # Segment if a file extension is present.
+      :suffix,              # The file extension of the filename.
+      :query,               # Params and values as a string.
+      :query_values,        # A hash of params and values.
+      :fragment,            # Fragment identifier.
+      :resource,            # Path, query, and fragment.
+      :location             # Directory and resource - everything after the site.
+    ]
+
+    def_delegators :@model, *COMPONENTS
+
+    def_delegator :@model, :parsed_domain
+    def_delegator :parsed_domain, :labels
+
+    attr_reader :input, :uri, :options
+
+    def initialize(uri, options = {}, &blk)
+      @input      = uri
+      @options    = set_options(options, &blk)
+      @block      = blk ? blk : block_builder
+      @uri        = UrlParser::Parser.call(@input, @options, &@block)
+      @model      = UrlParser::Model.new(@uri)
+    end
+
+    def unescaped?
+      !!options[:unescape]
+    end
+
+    def parsed?
+      true
+    end
+
+    def unembedded?
+      !!options[:unembed]
+    end
+
+    def canonicalized?
+      !!options[:canonicalize]
+    end
+
+    def normalized?
+      !!options[:normalize]
+    end
+
+    def cleaned?
+      !!options[:clean] || (
+        unescaped?      &&
+        parsed?         &&
+        unembedded?     &&
+        canonicalized?  &&
+        normalized?
+      )
+    end
+
+    def clean
+      if cleaned?
+        raw
+      else
+        UrlParser::Parser.call(@input, raw: true) { |uri| uri.clean! }
+      end
+    end
+
+    # Cleans and converts into a naked hostname
+    #
+    def canonical
+      opts = { raw: true }
+      curi = naked_hostname + location
+
+      UrlParser::Parser.call(curi, opts) do |uri|
+        uri.clean!
+      end.sub(/\A[a-z]+:\/\//i, '//')
+    end
+
+    def clean?
+      cleaned? || self.to_s == clean
+    end
+
+    def relative?
+      uri.relative?
+    end
+
+    def absolute?
+      uri.absolute?
+    end
+
+    def localhost?
+      !!(hostname.to_s[LOCALHOST_REGEXP])
+    end
+
+    def ipv4
+      hostname.to_s[Resolv::IPv4::Regex]
+    end
+
+    def ipv4?
+      !!ipv4
+    end
+
+    def ipv6
+      host.to_s[Resolv::IPv6::Regex]
+    end
+
+    def ipv6?
+      !!ipv6
+    end
+
+    def ip_address?
+      ipv4? || ipv6?
+    end
+
+    def naked?
+      !localhost? && www.nil?
+    end
+
+    def raw
+      uri.to_s
+    end
+    alias_method :to_s, :raw
+
+    def sha1
+      Digest::SHA1.hexdigest(raw)
+    end
+    alias_method :hash, :sha1
+
+    def ==(uri)
+      clean == self.class.new(uri, clean: true).clean
+    end
+
+    def =~(uri)
+      canonical == self.class.new(uri, clean: true).canonical
+    end
+
+    def +(uri)
+      self.class.new(uri.to_s, options.merge({ base_uri: self.to_s}), &@block)
+    end
+    alias_method :join, :+
+
+    def valid?
+      return false if input.nil? || relative?
+      return true if ip_address? || localhost?
+      parsed_domain.valid?
+    end
+
+    private
+
+    def set_options(opts = {}, &blk)
+      UrlParser::OptionSetter
+        .new(opts, &blk)
+        .to_hash
+        .merge(raw: false)
+    end
+
+    def block_builder
+      proc do |uri|
+        if cleaned?
+          uri.clean!
+        else
+          uri.unescape!     if unescaped?
+          uri.parse!        if parsed?
+          uri.unembed!      if unembedded?
+          uri.canonicalize! if canonicalized?
+          uri.normalize!    if normalized?
+        end
+      end
+    end
+
+  end
+end

data/lib/url_parser/version.rb

@@ -1,3 +1,3 @@
 module UrlParser
-  VERSION = "0.4.0"
+  VERSION = "0.5.0"
 end

data/spec/spec_helper.rb

@@ -1,4 +1,10 @@
+$LOAD_PATH.unshift File.expand_path('../../lib', __FILE__)
+
+require 'codeclimate-test-reporter'
+CodeClimate::TestReporter.start
+
 require "rspec"
+
 begin
   require "pry"
 rescue LoadError; end
@@ -7,19 +13,90 @@ require "url_parser"
 
 # This file was generated by the `rspec --init` command. Conventionally, all
 # specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
-# Require this file using `require "spec_helper"` to ensure that it is only
-# loaded once.
+# The generated `.rspec` file contains `--require spec_helper` which will cause this
+# file to always be loaded, without a need to explicitly require it in any files.
+#
+# Given that it is always loaded, you are encouraged to keep this file as
+# light-weight as possible. Requiring heavyweight dependencies from this file
+# will add to the boot time of your test suite on EVERY test run, even for an
+# individual file that may not need all of that loaded. Instead, consider making
+# a separate helper file that requires the additional dependencies and performs
+# the additional setup, and require it from the spec files that actually need it.
+#
+# The `.rspec` file also contains a few flags that are not defaults but that
+# users commonly want.
 #
 # See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
 RSpec.configure do |config|
-  config.run_all_when_everything_filtered = true
+
+  # rspec-expectations config goes here. You can use an alternate
+  # assertion/expectation library such as wrong or the stdlib/minitest
+  # assertions if you prefer.
+  config.expect_with :rspec do |expectations|
+    # This option will default to `true` in RSpec 4. It makes the `description`
+    # and `failure_message` of custom matchers include text for helper methods
+    # defined using `chain`, e.g.:
+    # be_bigger_than(2).and_smaller_than(4).description
+    #   # => "be bigger than 2 and smaller than 4"
+    # ...rather than:
+    #   # => "be bigger than 2"
+    expectations.include_chain_clauses_in_custom_matcher_descriptions = true
+  end
+
+  # rspec-mocks config goes here. You can use an alternate test double
+  # library (such as bogus or mocha) by changing the `mock_with` option here.
+  config.mock_with :rspec do |mocks|
+    # Prevents you from mocking or stubbing a method that does not exist on
+    # a real object. This is generally recommended, and will default to
+    # `true` in RSpec 4.
+    mocks.verify_partial_doubles = true
+  end
+
+  # These two settings work together to allow you to limit a spec run
+  # to individual examples or groups you care about by tagging them with
+  # `:focus` metadata. When nothing is tagged with `:focus`, all examples
+  # get run.
   config.filter_run :focus
-  config.raise_errors_for_deprecations!
+  config.run_all_when_everything_filtered = true
+
+  # Limits the available syntax to the non-monkey patched syntax that is recommended.
+  # For more details, see:
+  #   - http://myronmars.to/n/dev-blog/2012/06/rspecs-new-expectation-syntax
+  #   - http://teaisaweso.me/blog/2013/05/27/rspecs-new-message-expectation-syntax/
+  #   - http://myronmars.to/n/dev-blog/2014/05/notable-changes-in-rspec-3#new__config_option_to_disable_rspeccore_monkey_patching
+  config.disable_monkey_patching!
+
+  # This setting enables warnings. It's recommended, but in some cases may
+  # be too noisy due to issues in dependencies.
+  # config.warnings = true
+
+  # Many RSpec users commonly either run the entire suite or an individual
+  # file, and it's useful to allow more verbose output when running an
+  # individual spec file.
+  # if config.files_to_run.one?
+    # Use the documentation formatter for detailed output,
+    # unless a formatter has already been configured
+    # (e.g. via a command-line flag).
+    # config.default_formatter = 'doc'
+  # end
+
+  # Print the 10 slowest examples and example groups at the
+  # end of the spec run, to help surface which specs are running
+  # particularly slow.
+  # config.profile_examples = 10
+
   # Run specs in random order to surface order dependencies. If you find an
   # order dependency and want to debug it, you can fix the order by providing
   # the seed, which is printed after each run.
   #     --seed 1234
-  config.order = 'random'
-end
+  config.order = :random
 
+  # Seed global randomization in this process using the `--seed` CLI option.
+  # Setting this allows you to use `--seed` to deterministically reproduce
+  # test failures related to randomization by passing the same `--seed` value
+  # as the one that triggered the failure.
+  Kernel.srand config.seed
+
+end
 
+Dir[File.dirname(__FILE__) + "/support/**/*.rb"].each {|f| require f }

data/spec/support/helpers.rb

@@ -0,0 +1,7 @@
+RSpec.configure do |c|
+  c.around(:each, :disable_raise_error_warning) do |example|
+    RSpec::Expectations.configuration.warn_about_potential_false_positives = false
+    example.call
+    RSpec::Expectations.configuration.warn_about_potential_false_positives = true
+  end
+end

data/spec/url_parser/domain_spec.rb

@@ -0,0 +1,163 @@
+require 'spec_helper'
+
+RSpec.describe UrlParser::Domain do
+
+  context ".new" do
+
+    it "downcases the input" do
+      instance = described_class.new('EXAMPLE.COM')
+      expect(instance.original).to eq 'example.com'
+    end
+
+    it "removes the root label from absolute domains" do
+      instance = described_class.new('example.com.')
+      expect(instance.original).to eq 'example.com'
+    end
+
+    it "sets #original as the input string" do
+      instance = described_class.new("💩.la")
+      expect(instance.original).to eq "💩.la"
+    end
+
+    it "sets the name as a string containing only ASCII characters" do
+      instance = described_class.new("💩.la")
+      expect(instance.name).to eq "xn--ls8h.la"
+    end
+
+  end
+
+  context "#labels" do
+
+    it "returns an array of domain parts" do
+      instance = described_class.new('www.my.example.com')
+      expect(instance.labels).to eq(["com", "example", "my", "www"])
+    end
+
+  end
+
+  context "#suffix" do
+
+    it "when domain is valid, returns a PublicSuffix::Domain" do
+      instance = described_class.new('my.example.com')
+      expect(instance.suffix).to be_a PublicSuffix::Domain
+    end
+
+    it "with a PublicSuffix::Domain, a call to #to_s returns the domain" do
+      instance = described_class.new('my.example.com')
+      expect(instance.suffix.to_s).to eq 'my.example.com'
+    end
+
+    it "when domain is invalid, returns a OpenStruct" do
+      instance = described_class.new('//')
+      expect(instance.suffix).to be_a OpenStruct
+    end
+
+    it "when domain is invalid, a call to #to_s returns an empty string" do
+      instance = described_class.new('//')
+      expect(instance.suffix.to_s).to eq ''
+    end
+
+  end
+
+  context "#tld" do
+
+    it "when domain is valid, returns the top level domain" do
+      instance = described_class.new('www.my.example.com')
+      expect(instance.tld).to eq 'com'
+    end
+
+    it "when domain is invalid, returns nil" do
+      instance = described_class.new('//')
+      expect(instance.tld).to be_nil
+    end
+
+  end
+
+  context "#sld" do
+
+    it "when domain is valid, returns the second level domain" do
+      instance = described_class.new('www.my.example.com')
+      expect(instance.sld).to eq 'example'
+    end
+
+    it "when domain is invalid, returns nil" do
+      instance = described_class.new('//')
+      expect(instance.sld).to be_nil
+    end
+
+  end
+
+  context "#trd" do
+
+    it "when domain is valid, returns the third level domain" do
+      instance = described_class.new('www.my.example.com')
+      expect(instance.trd).to eq 'www.my'
+    end
+
+    it "when domain is invalid, returns nil" do
+      instance = described_class.new('//')
+      expect(instance.trd).to be_nil
+    end
+
+  end
+
+  context "#valid?" do
+
+    it "does not fail on an empty string" do
+      instance = described_class.new("")
+      expect(instance).not_to be_valid
+    end
+
+    it "is false when containing invalid characters" do
+      instance = described_class.new('my&example.com')
+      expect(instance).not_to be_valid
+      expect(instance.errors).to include "contains invalid characters"
+    end
+
+    it "is true with a valid suffix" do
+      instance = described_class.new('example.co.uk')
+      expect(instance).to be_valid
+    end
+
+    it "is false with an invalid suffix" do
+      instance = described_class.new('//')
+      expect(instance).not_to be_valid
+      expect(instance.errors).to include "'//' is not a valid domain"
+    end
+
+    it "is true with 127 labels or less" do
+      instance = described_class.new('.'*126+'com')
+      expect(instance).to be_valid
+    end
+
+    it "is false when exceeding 127 labels" do
+      instance = described_class.new('.'*127+'com')
+      expect(instance).not_to be_valid
+      expect(instance.errors).to include "exceeds 127 labels"
+    end
+
+    it "is true when no labels are greater than 63 characters" do
+      instance = described_class.new('a'*63+'.com')
+      expect(instance).to be_valid
+    end
+
+    it "is false with labels greater than 63 characters" do
+      instance = described_class.new('a'*64+'.com')
+      expect(instance).not_to be_valid
+      expect(instance.errors).to include "exceeds maximum label length of 63 characters"
+    end
+
+    it "is true with 253 ASCII characters or less" do
+      instance = described_class.new('a'*49+'.'+'b'*49+'.'+'c'*49+'.'+'d'*49+'.'+'e'*49+'.com')
+      expect(instance).to be_valid
+    end
+
+    it "is true with 253 ASCII characters or less" do
+      instance = described_class.new('a'*49+'.'+'b'*49+'.'+'c'*49+'.'+'d'*49+'.'+'e'*49+'.aero')
+      expect(instance).not_to be_valid
+      expect(instance.errors).to include "exceeds 253 ASCII characters"
+    end
+
+  end
+
+end